Data Transformation Methods Research Articles

Optimizing a Dynamic Vehicle Routing Problem with Deep Reinforcement Learning: Analyzing State-Space Components

Background: The dynamic vehicle routing problem (DVRP) is a complex optimization problem that is crucial for applications such as last-mile delivery. Our goal is to develop an application that can make real-time decisions to maximize total performance while adapting to the dynamic nature of incoming orders. We formulate the DVRP as a vehicle routing problem where new customer requests arrive dynamically, requiring immediate acceptance or rejection decisions. Methods: This study leverages reinforcement learning (RL), a machine learning paradigm that operates via feedback-driven decisions, to tackle the DVRP. We present a detailed RL formulation and systematically investigate the impacts of various state-space components on algorithm performance. Our approach involves incrementally modifying the state space, including analyzing the impacts of individual components, applying data transformation methods, and incorporating derived features. Results: Our findings demonstrate that a carefully designed state space in the formulation of the DVRP significantly improves RL performance. Notably, incorporating derived features and selectively applying feature transformation enhanced the model’s decision-making capabilities. The combination of all enhancements led to a statistically significant improvement in the results compared with the basic state formulation. Conclusions: This research provides insights into RL modeling for DVRPs, highlighting the importance of state-space design. The proposed approach offers a flexible framework that is applicable to various variants of the DVRP, with potential for validation using real-world data.

The effectiveness of data pre-processing methods on the performance of machine learning techniques using RF, SVR, Cubist and SGB: a study on undrained shear strength prediction

In the field of data engineering in machine learning (ML), a crucial component is the process of scaling, normalization, and standardization. This process involves transforming data to make it more compatible with modeling techniques. In particular, this transformation is essential to ensure the suitability of the data for subsequent analysis. Despite the application of many conventional and relatively new approaches to ML, there remains a conspicuous lack of research, particularly in the geotechnical discipline. In this study, ML-based prediction models (i.e., RF, SVR, Cubist, and SGB) were developed to estimate the undrained shear strength (UDSS) of cohesive soil from the perspective of a wide range of data-scaling and transformation methods. Therefore, this work presents a novel ML framework based on data engineering approaches and the Cubist regression method to predict the UDSS of cohesive soil. A dataset including six different features and one target variable were used for building prediction models. The performance of ML models was examined considering the impact of the data pre-processing issue. For that purpose, data scaling and transformation methods, namely Range, Z-Score, Log Transformation, Box-Cox, and Yeo-Johnson, were used to generate the models. The results were then systematically compared using different sampling ratios to understand how model performance varies as various data scaling/transformation methods and ML algorithms were combined. It was observed that data transformation or data sampling methods had considerable or limited effects on the UDSS model performance depending on the algorithm type and the sampling ratio. Compared to RF, SVR, and SGB models, Cubist models provided higher performance metrics after applying the data pre-processing steps. The Box-Cox transformed Cubist model yielded the best prediction performance among the other models with an R2 of 0.87 for the 90% training set. Also, the UDSS prediction model generally yielded the best performance metrics when it was used with the transformed-based models (i.e., Box-Cox, Log, and Yeo-Johnson) than that of scaled-based (i.e., Range and Z-Score) models. The results show that the Cubist model has a higher potential for UDSS prediction, and data pre-processing methods have impacts on the predictive capacity of the evaluated regression models.

Digital Twin Smart City: Integrating IFC and CityGML with Semantic Graph for Advanced 3D City Model Visualization

The growing interest in building data management, especially the building information model (BIM), has significantly influenced urban management, materials supply chain analysis, documentation, and storage. However, the integration of BIM into 3D GIS tools is becoming more common, showing progress beyond the traditional problem. To address this, this study proposes data transformation methods involving mapping between three domains: industry foundation classes (IFC), city geometry markup language (CityGML), and web ontology framework (OWL)/resource description framework (RDF). Initially, IFC data are converted to CityGML format using the feature manipulation engine (FME) at CityGML standard’s levels of detail 4 (LOD4) to enhance BIM data interoperability. Subsequently, CityGML is converted to the OWL/RDF diagram format to validate the proposed BIM conversion process. To ensure integration between BIM and GIS, geometric data and information are visualized through Cesium Ion web services and Unreal Engine. Additionally, an RDF graph is applied to analyze the association between the semantic mapping of the CityGML standard, with Neo4j (a graph database management system) utilized for visualization. The study’s results demonstrate that the proposed data transformation methods significantly improve the interoperability and visualization of 3D city models, facilitating better urban management and planning.

Research on LiDAR point cloud data transformation method based on weighted altitude difference map

Road surface detection plays a pivotal role in the realm of autonomous vehicle navigation. Contemporary methodologies primarily leverage LiDAR for acquiring three-dimensional data and utilize imagery for chromatic information. However, these approaches encounter significant integration challenges, particularly due to the inherently unstructured nature of 3D point clouds. Addressing this, our novel algorithm, specifically tailored for predicting drivable areas, synergistically combines LiDAR point clouds with bidimensional imagery. Initially, it constructs an altitude discrepancy map via LiDAR, capitalizing on the height uniformity characteristic of planar road surfaces. Subsequently, we introduce an innovative and more efficacious attention mechanism, streamlined for image feature extraction. This mechanism employs adaptive weighting coefficients for the amalgamation of the altitude disparity imagery and two-dimensional image features, thereby facilitating road area delineation within a semantic segmentation framework. Empirical evaluations conducted using the KITTI dataset underscore our methodology’s superior road surface discernment and extraction precision, substantiating the efficacy of our proposed network architecture and data processing paradigms. This research endeavor seeks to propel the advancement of three-dimensional perception technology in the autonomous driving domain.

Prediction of Student Dropout in Malaysian’s Private Higher Education Institute using Data Mining Application

Student dropout issue is a major concern among the academics and management of the university. The higher rate of student dropout impacted the university reputation such as reducing student enrolment, affecting the revenue of the university, financial losses for the country, and increase the existence of a social problem among the students. In this study, 2 popular classifiers were utilized to predict the student dropout namely decision tree and logistic regression model respectively. Several sets of experimental setting were employed which include three set of data partitioning - along with different types of decision tree and regression model. As for the logistic regression model, different data imputation and transformation method was tested to ensure that the model built is valid. A total of 7706 student data extracted from one of the private universities in Malaysia database (between year 2018-2019) to assess the capability of the classifier. The classifier performance is evaluated using machine learning performance measure of accuracy and misclassification rate. The result indicates that, decision tree - chi-square (2 branches) achieved slightly better classification performance of 89.49% on 80/20 data partitioning. The chosen model also identified the most important variable for accurate prediction of student dropout. Application of this model has the potential to accurately predict at risk student and to reduce student dropout rates.

Development and external validation of deep learning clinical prediction models using variable-length time series data.

To compare and externally validate popular deep learning model architectures and data transformation methods for variable-length time series data in 3 clinical tasks (clinical deterioration, severe acute kidney injury [AKI], and suspected infection). This multicenter retrospective study included admissions at 2 medical centers that spanned 2007-2022. Distinct datasets were created for each clinical task, with 1 site used for training and the other for testing. Three feature engineering methods (normalization, standardization, and piece-wise linear encoding with decision trees [PLE-DTs]) and 3 architectures (long short-term memory/gated recurrent unit [LSTM/GRU], temporal convolutional network, and time-distributed wrapper with convolutional neural network [TDW-CNN]) were compared in each clinical task. Model discrimination was evaluated using the area under the precision-recall curve (AUPRC) and the area under the receiver operating characteristic curve (AUROC). The study comprised 373825 admissions for training and 256128 admissions for testing. LSTM/GRU models tied with TDW-CNN models with both obtaining the highest mean AUPRC in 2 tasks, and LSTM/GRU had the highest mean AUROC across all tasks (deterioration: 0.81, AKI: 0.92, infection: 0.87). PLE-DT with LSTM/GRU achieved the highest AUPRC in all tasks. When externally validated in 3 clinical tasks, the LSTM/GRU model architecture with PLE-DT transformed data demonstrated the highest AUPRC in all tasks. Multiple models achieved similar performance when evaluated using AUROC. The LSTM architecture performs as well or better than some newer architectures, and PLE-DT may enhance the AUPRC in variable-length time series data for predicting clinical outcomes during external validation.

Towards enhanced surface roughness modeling in machining: an analysis of data transformation techniques

Data transformation methods are utilized to convert datasets into non-integer formats, potentially altering their distribution patterns. This implies that the variance and standard deviation of the dataset may be altered after the dataset undergoes data transformation operations. Improving model accuracy is a primary application of these methods. This study compares the efficacy of three data transformation techniques: square root transformation, logarithmic transformation, and inverse transformation. The comparison is conducted within the context of developing a surface roughness model for a turning process. Eighteen experiments are performed using the Box-Behnken method, with surface roughness chosen as the response variable. The surface roughness dataset undergoes transformation using the mentioned methods. Four surface roughness regression models are then built: one without transformation, one with square root transformation, one with logarithmic transformation, and one with inverse transformation. Evaluation metrics include coefficient of determination (R-Sq), adjusted coefficient of determination (R-Sq(adj)), Mean Absolute Error (%MAE), and Mean Squared Error (%MSE). Results indicate logarithmic transformation as the most effective, followed by square root transformation, in enhancing model accuracy. The surface roughness model utilizing data transformation exhibits high R-Sq and R-Sq(adj) values, at 0.8792 and 0.7434 respectively. On the other hand, this model has %MAE and %MSE values of only 10.33 and 2.05 respectively. Conversely, inverse transformation exhibits the least effectiveness among the three methods

A Note on Zero-Sum Two-Person Undiscounted One Player Control Semi-Markov Games

Zero-sum two-person finite undiscounted (limiting ratio average) semi-Markov games are considered where both the transition probabilities and the transition times are controlled by a fixed player in all states. We prove that, if such a game is unichain, the value and optimal stationary strategies of the players can be obtained from an optimal solution of the linear programming algorithm for the associated one player control stochastic game using a data transformation method. An example is provided for such class of games.

Comparison of the effectiveness of different normalization methods for metagenomic cross-study phenotype prediction under heterogeneity

The human microbiome, comprising microorganisms residing within and on the human body, plays a crucial role in various physiological processes and has been linked to numerous diseases. To analyze microbiome data, it is essential to account for inherent heterogeneity and variability across samples. Normalization methods have been proposed to mitigate these variations and enhance comparability. However, the performance of these methods in predicting binary phenotypes remains understudied. This study systematically evaluates different normalization methods in microbiome data analysis and their impact on disease prediction. Our findings highlight the strengths and limitations of scaling, compositional data analysis, transformation, and batch correction methods. Scaling methods like TMM show consistent performance, while compositional data analysis methods exhibit mixed results. Transformation methods, such as Blom and NPN, demonstrate promise in capturing complex associations. Batch correction methods, including BMC and Limma, consistently outperform other approaches. However, the influence of normalization methods is constrained by population effects, disease effects, and batch effects. These results provide insights for selecting appropriate normalization approaches in microbiome research, improving predictive models, and advancing personalized medicine. Future research should explore larger and more diverse datasets and develop tailored normalization strategies for microbiome data analysis.

Comparison of surface-wave techniques to estimate S- and P-wave velocity models from active seismic data

Abstract. The acquisition of seismic exploration data in remote locations presents several logistical and economic criticalities. The irregular distribution of sources and/or receivers facilitates seismic acquisition operations in these areas. A convenient approach is to deploy nodal receivers on a regular grid and to use sources only in accessible locations, creating an irregular source–receiver layout. It is essential to evaluate, adapt, and verify processing workflows, specifically for near-surface velocity model estimation using surface-wave analysis, when working with these types of datasets. In this study, we applied three surface-wave techniques (i.e., wavelength–depth (W/D) method, laterally constrained inversion (LCI), and surface-wave tomography (SWT)) to a large-scale 3D dataset obtained from a hard-rock site using the irregular source–receiver acquisition method. The methods were fine-tuned for the data obtained from hard-rock sites, which typically exhibit a low signal-to-noise ratio. The wavelength–depth method is a data transformation method that is based on a relationship between skin depth and surface-wave wavelength and provides both S- and P-wave velocity (Vs and Vp) models. We used Poisson's ratios estimated through the wavelength–depth method to constrain the laterally constrained inversion and surface-wave tomography and to retrieve both Vs and Vp also from these methods. The pseudo-3D Vs and Vp models were obtained down to 140 m depth over an area of approximately 900 × 1500 m2. The estimated models from the methods matched the geological information available for the site. A difference of less than 6 % was observed between the estimated Vs models from the three methods, whereas this value was 7.1 % for the retrieved Vp models. The methods were critically compared in terms of resolution and efficiency, which provides valuable insights into the potential of surface-wave analysis for estimating near-surface models at hard-rock sites.

On the use of machine learning and data-transformation methods to predict hydration kinetics and strength of alkali-activated mine tailings-based binders

The escalating production of mine tailings (MT), a byproduct of the mining industry, constitutes significant environmental and health hazards, thereby requiring a cost-effective and sustainable solution for its disposal or reuse. This study proposes the use of MT as the primary ingredient (≥70%mass) in binders for construction applications, thereby ensuring their efficient upcycling as well as drastic reduction of environmental impacts associated with the use of ordinary Portland cement (OPC). The early-age hydration kinetics and compressive strength of MT-based binders are evaluated with an emphasis on elucidating the influence of alkali activation parameters and the amount of slag or cement that are used as minor constituents. This study reveals correlations between cumulative heat release and compressive strengths at different ages; these correlations can be leveraged to estimate the compressive strength based on hydration kinetics. Furthermore, this study presents a random forest (RF) model—in conjunction with fast Fourier and direct cosine transformation techniques to overcome the limitations associated with limited volume and diversity of the database—to enable high-fidelity predictions of time-dependent hydration kinetics and compressive strength of MT-based binders in relation to mixture design. Overall, this study demonstrates a sustainable approach to upcycle mine tailings as the primary component in low-carbon construction binders; and presents both analytical and machine learning-based approaches for accurate a priori predictions of hydration kinetics and compressive strength of these binders.

Improving Anomaly Classification using Combined Data Transformation and Machine Learning Methods

Improving Anomaly Classification using Combined Data Transformation and Machine Learning Methods

Multi-Stimulus Least-Squares Transformation With Online Adaptation Scheme to Reduce Calibration Effort for SSVEP-Based BCIs.

The proposed ms-LST-OA consists of two parts. Firstly, to improve the precision of the transformation matrices, we propose the multi-stimulus LST (ms-LST) using cross-stimulus learning scheme as the cross-subject data transformation method. The ms-LST uses the data from neighboring stimuli to construct a higher precision transformation matrix for each stimulus to reduce the differences between transformed data and real data. Secondly, to further optimize the constructed spatial filters and reference templates, we use an online adaptation scheme to learn more features of the EEG signals of the target subject through an iterative process trial-by-trial. ms-LST-OA performance was measured for three datasets (Benchmark Dataset, BETA Dataset, and UCSD Dataset). Using few calibration data, the ITR of ms-LST-OA achieved 210.01±10.10 bits/min, 172.31±7.26 bits/min, and 139.04±14.90 bits/min for all three datasets, respectively. Using ms-LST-OA can reduce calibration effort for SSVEP-based BCIs.

Hyperspectral imaging detects biological stress of wheat for early diagnosis of crown rot disease

Crown rot, caused by a stubble-soil fungal pathogen, threatens wheat production, leading to significant yield losses. The challenge lies in the absence of early visible symptoms for timely detection and management. While hyperspectral imaging technologies have been successfully applied to improve screening for some plant health indicators and diseases, they have not yet been successfully used for crown rot disease detection. This study endeavoured to harness hyperspectral imaging technologies for early-stage, high-throughput, accurate, economical, and non-destructive detection of crown rot disease. Four common Australian commercial wheat varieties with different resistance levels were chosen for study, including Aurora, Yitpi, Emu Rock and Trojan. Three different hyperspectral cameras, covering various wavelength ranges, were tested from both side-view and top-view. Four types of input data for support vector machine classification were tested, including reflectance and the other three derived forms namely hyper-hue, standard normal variate, and principal components. The experimental results showed that hyperspectral imaging technologies can successfully diagnose infected plants in a greenhouse approximately 30 days after infection when there were no visible symptoms on shoots, and the hyper-hue and standard normal variate data transformation methods achieved high F1 scores above 0.75. By discovering key wavelengths, we found that hyperspectral imaging achieved early detection by uncovering biological stress related to photosynthetic activities, and limited absorption of water, protein and starch synthesis. These findings represent a critical advance towards establishing a hyperspectral imaging system for crown rot detection, thereby facilitating disease management and breeding resistant varieties.

Evaluating the Impact of Data Transformation Techniques on the Performance and Interpretability of Software Defect Prediction Models

The performance of software defect prediction (SDP) models determines the priority of test resource allocation. Researchers also use interpretability techniques to gain empirical knowledge about software quality from SDP models. However, SDP methods designed in the past research rarely consider the impact of data transformation methods, simple but commonly used preprocessing techniques, on the performance and interpretability of SDP models. Therefore, in this paper, we investigate the impact of three data transformation methods (Log, Minmax, and Z-score) on the performance and interpretability of SDP models. Through empirical research on (i) six classification techniques (random forest, decision tree, logistic regression, Naive Bayes, K-nearest neighbors, and multilayer perceptron), (ii) six performance evaluation indicators (Accuracy, Precision, Recall, F1, MCC, and AUC), (iii) two interpretable methods (permutation and SHAP), (iv) two feature importance measures (Top-k feature rank overlap and difference), and (v) three datasets (Promise, Relink, and AEEEM), our results show that the data transformation methods can significantly improve the performance of the SDP models and greatly affect the variation of the most important features. Specifically, the impact of data transformation methods on the performance and interpretability of SDP models depends on the classification techniques and evaluation indicators. We observe that log transformation improves NB model performance by 7%–61% on the other five indicators with a 5% drop in Precision. Minmax and Z-score transformation improves NB model performance by 2%–9% across all indicators. However, all three transformation methods lead to substantial changes in the Top-5 important feature ranks, with differences exceeding 2 in 40%–80% of cases (detailed results available in the main content). Based on our findings, we recommend that (1) considering the impact of data transformation methods on model performance and interpretability when designing SDP approaches as transformations can improve model accuracy, and potentially obscure important features, which lead to challenges in interpretation, (2) conducting comparative experiments with and without the transformations to validate the effectiveness of proposed methods which are designed to improve the prediction performance, and (3) tracking changes in the most important features before and after applying data transformation methods to ensure precise and traceable interpretability conclusions to gain insights. Our study reminds researchers and practitioners of the need for comprehensive considerations even when using other similar simple data processing methods.

Evaluating The Data Analytics For Finance And Insurance Sectors For Industry 4.0

The insurance industry relies heavily on statistics, despite the absence of a physical good or service being sold. A financial, risk, consumer, producer, and actuarial database would be created by such an industry. In prior decades, these sectors gathered structured data that they augmented with product and policyholder details. However, semi- and unstructured data represent a massive untapped resource. This will also prevent the insurance from making the most of the information it collects. Despite the striking similarities between healthcare delivery and insurance funding, life insurer problems have hampered the field for the better part of a century. Organizations that need both unstructured and structured data to flourish can find the optimal places to store both types of data according to research. The insurance industry may make better use of data with the help of applied analytics. The insurance industry is also discussed in relation to big data adoption techniques such as training, research, collaboration, and implementation. Several models of the data adoption and transformation methods that contribute to the insurance sector's extraordinary data analysis and forecasting abilities are shown in this article, which delves into the data transformation practises of the insurance business. Healthcare delivery systems need to be overhauled for "Big Data Analytics" to be of any real use. The purpose of this study is to investigate the ways in which modern data management has changed the insurance sector, as well as the traits and applications that have paved the way for the emergence of cutting-edge tools and the expansion of the economy.

Selection of strawberry cultivars according to their productivity and berry quality using normalized indices

Background. Combined use of various data transformation methods and a multivariate statistical analysis that takes into account several variables would increase the efficiency of selecting promising strawberry genotypes according to a set of traits for industrial and small-scale production.Materials and methods. In 2020–2022, 17 short-day garden strawberry cultivars were studied. The analysis was carried out for productivity (the number of berries, the weight of berries of the 1st order, and the average berry weight), marketable quality of berries (berry pulp density, berry height, and berry diameter), and total weight of berries per plant. Mathematical data processing employed a two-factor analysis of variance, the principal component method, cluster analysis by Ward’s algorithm, and Wilcoxon test.Results. The statistical significance of the cultivar and year factors, and their interaction was measured. The cultivar’s genotype had the greatest effect on the variability of characters. Greater part of the total variance in the set of characters was determined by the first five principal components. The cluster analysis identified two groups of cultivars. The initial data were transformed according to the least significant difference (LSD05) to obtain normalized indices. Taking into account the Wilcoxon test, the cultivars were ranked by the indices. When comparing the groups built in line with mean and total values of the normalized indices with the cluster analysis results, 6 best strawberry cultivars were identified for the studied set of characters.Conclusion. The combined use of multivariate methods and normalized indices made it possible to identify the most promising strawberry cultivars according to their yield and berry quality: ‘Olympia’, ‘Nelli’, ‘Florence’, ‘Kemia’, ‘Jive’, and ‘Alba’.

Studying Imbalanced Learning for Anomaly-Based Intelligent IDS for Mission-Critical Internet of Things

Training-anomaly-based, machine-learning-based, intrusion detection systems (AMiDS) for use in critical Internet of Things (CioT) systems and military Internet of Things (MioT) environments may involve synthetic data or publicly simulated data due to data restrictions, data scarcity, or both. However, synthetic data can be unrealistic and potentially biased, and simulated data are invariably static, unrealistic, and prone to obsolescence. Building an AMiDS logical model to predict the deviation from normal behavior in MioT and CioT devices operating at the sensing or perception layer due to adversarial attacks often requires the model to be trained using current and realistic data. Unfortunately, while real-time data are realistic and relevant, they are largely imbalanced. Imbalanced data have a skewed class distribution and low-similarity index, thus hindering the model’s ability to recognize important features in the dataset and make accurate predictions. Data-driven learning using data sampling, resampling, and generative methods can lessen the adverse impact of a data imbalance on the AMiDS model’s performance and prediction accuracy. Generative methods enable passive adversarial learning. This paper investigates several data sampling, resampling, and generative methods. It examines their impacts on the performance and prediction accuracy of AMiDS models trained using imbalanced data drawn from the UNSW_2018_IoT_Botnet dataset, a publicly available IoT dataset from the IEEEDataPort. Furthermore, it evaluates the performance and predictability of these models when trained using data transformation methods, such as normalization and one-hot encoding, to cover a skewed distribution, data sampling and resampling methods to address data imbalances, and generative methods to train the models to increase the model’s robustness to recognize new but similar attacks. In this initial study, we focus on CioT systems and train PCA-based and oSVM-based AMiDS models constructed using low-complexity PCA and one-class SVM (oSVM) ML algorithms to fit an imbalanced ground truth IoT dataset. Overall, we consider the rare event prediction case where the minority class distribution is disproportionately low compared to the majority class distribution. We plan to use transfer learning in future studies to generalize our initial findings to the MioT environment. We focus on CioT systems and MioT environments instead of traditional or non-critical IoT environments due to the stringent low energy, the minimal response time constraints, and the variety of low-power, situational-aware (or both) things operating at the sensing or perception layer in a highly complex and open environment.

Advancing chirality analysis through enhanced enantiomer characterization and quantification via fast Fourier transform capacitance voltammetry

The exploration of the chiral configurations of enantiomers represents a highly intriguing realm of scientific inquiry due to the distinct roles played by each enantiomer (D and L) in chemical reactions and their practical utilities. This study introduces a pioneering analytical methodology, termed fast Fourier transform capacitance voltammetry (FFT-CPV), in conjunction with principal component analysis (PCA), for the identification and quantification of the chiral forms of tartaric acid (TA), serving as a representative model system for materials exhibiting pronounced chiral characteristics. The proposed methodology relies on the principle of chirality, wherein the capacitance signal generated by the adsorption of D-TA and L-TA onto the surface of a platinum electrode (Pt-electrode) in an acidic solution is harnessed. The capacitance voltammograms were meticulously recorded under optimized experimental conditions. To compile the final dataset for the analyte, the average of the FFT capacitance voltammograms of the acidic solution (without the presence of the analyte) was subtracted from those containing the analyte. A distinct arrangement was obtained by employing PCA as a linear data transformation method, representing D-TA and L-TA in a two/three-dimensional space. The outcomes of the study reveal the successful detection of the two chiral forms of TA with a considerable degree of precision and reproducibility. Moreover, the proposed method facilitated the establishment of two linear response ranges for the concentration values of each enantiomer, spanning from 1 to 20 µM, and 50 to 500 µM. The respective detection limits were also determined to be 0.4 µM for L-TA and 1.3 µM for D-TA. These findings underscore the satisfactory sensitivity and efficiency of the proposed method in both qualitative and quantitative assessments of the chiral forms of TA.

Capacity prediction and design optimization for laterally loaded monopiles in sandy soil using hybrid neural network and sequential quadratic programming

Data driven methods have gained momentum in recent years in solving highly non-linear engineering problems that are challenging to solve using conventional methods. In this paper, we present a hybrid neural network model to predict the lateral response of large-diameter monopiles in multi-layered soil. The hybrid neural network consists of a mixture of convolutional and fully-connected layers, which capture the impacts of the soil profile, the pile geometry, and loading conditions on the lateral load response of monopiles. To train the neural network model, we produced data from high-fidelity three-dimensional (3D) finite element (FE) models that are validated against full-scale pile load tests. To ensure consistent model performance across the entire range of pile capacities considered in the dataset (ranging from approximately 100 kN to 100,000 kN), we utilize the relative error (percentage error) as the criterion for training the model. To achieve this goal, we explored six different combinations of data transformation methods (i.e., natural logarithm and root transformations) and cost functions. Among these models, the model trained with Mean Squared Error (MSE) using natural logarithm transformation yielded the most accurate and consistent predictions of the lateral capacities of monopiles. To demonstrate the strengths of the developed neural network model, it was used as a surrogate model to perform pile design optimization using sequential quadratic programming. In addition, a design example is provided to show how the developed method can be easily implemented.