PREDICTIVE MODELING OF BRIDGE LOAD CAPACITY USING MACHINE LEARNING AND REAL-TIME SENSOR DATA

Oilseed rape, as one of the most important oil crops, is an important source of vegetable oil and protein for mankind. As a non-essential element for plant growth, heavy metal cadmium (Cd) is easily absorbed by plants. Cd will inhibit the photosynthesis of plants, destroy the cell structure, slow the growth of plants, and affect their development and yield. It is necessary to develop a method based on visible near-infrared (NIR) hyperspectral imaging (HSI) technology to quickly and nondestructively determine the Cd content in rape leaves. Two-layer estimation models were established by combining visible-NIR HSI with ensemble learning methods (stacking and blending). One layer used support vector regression, extreme learning machine, decision tree, and random forest (RF) as basic learners, and the other layer used support vector regression or RF as a meta learner. Different models were used to analyze the spectra of rape treated with five Cd concentrations to obtain the best prediction method. The results showed that the best model to predict Cd content was the stacking ensemble model with RF as the meta learner, with coefficient of determination for prediction of 0.9815 and root-mean-square error for prediction of 5.8969 mg kg-1 . A pseudo-color image was developed using this stacking model to visualize the content and distribution of Cd. The combination of visible-NIR HSI technology and the stacking ensemble learning method is a feasible method to detect the Cd content in rape leaves, which has the potential of being rapid and nondestructive. © 2022 Society of Chemical Industry.

In this paper, the Support Vector Regression (SVR) technique is use for speed estimation of a Three Phase Induction Motor (TIM) by the dynamic strain measurement analysis running at different load condition. The dynamic strain induced by mechanical and electrical forces is measure by fiber Bragg gratings (FBGs), installed inside the motor, in between two stator teeth. A frequency inverter driver is operating at 60 Hz to run the motor at 0%, 23.15%, 36.28%, 40.03% and 41.3% of the nominal load. The speed is estimate based on SVR with a maximum absolute error of 0.2%. The dynamic strain measured by FBGs has a good signal-to-noise ratio due to the intrinsic characteristics of optical sensors.

Binary dynamic stochastic search algorithm with support vector regression for feature selection in low-velocity impact localization problem

Flow Accelerated Corrosion (FAC) is a critical degradation mechanism in high-temperature, high-pressure (HTHP) systems such as nuclear and fossil power plants. Accurate prediction of FAC is essential for ensuring reliability, safety, and cost-effective maintenance. This work presents a data-driven framework that integrates Big Data analytics with advanced Machine Learning (ML) methods to analyze and predict FAC under simulated HTHP conditions. A comprehensive dataset was developed from experimental studies and published literature, incorporating key parameters such as temperature, pressure, velocity, dissolved oxygen, and pH. Multiple ML algorithms were evaluated, including Linear Regression, Polynomial Regression, Random Forest, Support Vector Regression (SVR), and Multi-Layer Perceptron (MLP). Results show that while Linear Regression yielded limited accuracy (R2 ≈ 0.50), advanced approaches significantly improved predictions. Polynomial Regression achieved R2 ≈ 0.92, Random Forest reached R2 ≈ 0.89, SVR attained R2 ≈ 0.98, and the best performance was achieved by MLP with R2 ≈ 0.96 and lowest error (MAE = 0.06). These findings highlight the strong potential of ML for developing robust predictive models, supporting risk management strategies, and advancing digital solutions for resilient energy systems.

In this paper, a novel support vector machine (SVM) learning approach has been used to predict the silt erosion of coatings sprayed by the high-velocity oxy-fuel (HVOF) process. The silt erosion resistance of HVOF-coated Co- and Ni-alloys is studied using an erosion tester. Both of these spraying powders were deposited on the 18Cr-12Ni-2Mo austenitic steel substrate. For the erosion experiments, the fixtures were developed to test the erosion characteristics at different impingement conditions (i.e. [Formula: see text], [Formula: see text], and [Formula: see text]). The image processing technique enables an understanding of the erosion mechanisms of coatings. The support vector regression is more effective than the traditional regression models. The proposed model employs support vector regression with parameter tuning. The ideal parameters are selected with the help of the grid search method. The model is trained by supplying 70% data and validated with 15% data. Afterward, the remaining 15% is given to the prepared model as testing data. The dataset obtained is employed for building an effective support vector regression model. The predicted results are compared against the original experimental values. The developed model is also compared with other state-of-the-art machine learning techniques for showing the preciseness of the proposed model. The Ni-based HVOF coating showed superior performance ([Formula: see text]) better than the Co-based HVOF coating under similar experimental conditions. An SVM model was successfully developed to predict the erosion of coated and uncoated 18Cr-12Ni-2Mo austenitic steel. The precision performance of the SVM model was calculated in terms of [Formula: see text], RMSE, R, and MAE as 0.99, [Formula: see text], 0.99, and [Formula: see text], respectively.

On the model, in the five cases of missing central incisors or lateral incisors, I picked some teeth in various combinations as abutment teeth, analyzed movement of the loaded bridges, compared each capacity to load and got the following conclusion:1. The load-capacity index that was in proportion to the capacity of bridges to load was gotten.2. The relation between load-capacity index and suitability of bridges was examined from the three-dimensional movement of bridges and got the following criteria:1) load-capacity inde≥20: suitable for bridge2) load-capacity index 13∼19: border areasuitable for the bridge that abutment teeth at the both sides of missing teeth have balancedresistancenot suitable for the bridge that abutment teeth at the both sides of missing teeth have unbalanced resistance3) load-capacity index≤12: not suitable for bridge3. Considering the load-capacity index and the three-dimensional movement of bridges, suitable designs of bridges are following:(1) |1 (2), (3)(2) 1|1 (2)(3), (1) |12 (3), (3)(2) 1|12 (3)(4), (3) 1|12 (3)(4)

European Exchange Trading Funds Trading with Locally Weighted Support Vector Regression

In the field of sustainable mobility, this study highlights the importance of using machine learning for predictive modeling based on real traffic data collected from instrumented bicycles. The advent of advanced technologies like sustainable mobility apps, sensors, and advanced data analysis methods led to the ability to collect data from various sources, which enabled researchers to estimate battery state of charge (SOC) accurately. Most current research uses them in the lab experiments for data collection. In this work, we use real-time sensors data to construct data-driven models for lithium-ion battery SOC estimation. This research integrates both electric bicycle battery, environmental and route variables to achieve the following goals: (1) Collect a multimodal data set including operational, topography, vehicle, and external variables, (2) Preprocess data obtained from sensors installed on the electric bicycle battery, (3) Create models of lithium-ion battery SOC based on electric bicycle battery and environmental variables, and (4) Assess data-driven models and compare their performance for lithium-ion battery SOC with high accuracy. To achieve that, we conducted a real study to predict the Remaining Useful Life (RUL), as a measure of state of charge, of electric bicycle battery. The study was carried out on a 15 km cycle route in Medellín, Colombia, for 28 days. To estimate the RUL, we used four different machine learning algorithms: Long Short-Term Memory (LSTM), Support Vector Regression (SVR), AdaBoost, and Gradient Boost. Notably, data preprocessing techniques played a pivotal role, with a particular focus on smoothing sensor data using Convolutional Neural Networks (CNN). The results showed a significant improvement in prediction accuracy when using data preprocessing, confirming its importance in improving model performance. Furthermore, the comparison of network performance facilitated the selection of the most effective model for the test data. This study underscores the value of using real-world data to develop and validate predictive models in the pursuit of sustainable mobility solutions, and highlights the critical role of data-driven methodologies in addressing today's urban transportation challenges.

This study investigates the effectiveness of embedding fiber Bragg grating (FBG) sensors in power transmission towers to assess the remaining service life of the structures following impacts from strong winds and hurricanes. FBG sensors monitor the structural integrity of the tower using online measurement of strain variations at critical structural points. The novelty of this work lies in employing a compact long short-term memory (LSTM) framework to estimate the remaining useful lifetime (RUL) from real-time FBG sensor data under both stable and fluctuating wind conditions. To estimate RUL of the tower, LSTM neural network has been implemented, providing predictive insights for proactive maintenance and risk mitigation. A prototype transmission tower was built and experimentally evaluated in a wind tunnel to assess the effectiveness and performance of the proposed RUL model. To simulate different hurricane categories, the experiment was conducted across wind speeds between 0 and 150 mph. FBG sensors installed at critical locations continuously captured real-time strain data, which was transmitted via a low-power micro FBG interrogator to a computer for input into the RUL prediction model. The proposed three-layer LSTM converges rapidly, reducing training and validation loss by nearly two orders of magnitude within 40 epochs, and achieves robust RUL predictions with an average bias of about 50 s on the test set. To quantify structural health, a mathematical health indicator was formulated based on the observed strain responses. The FBG sensors demonstrated high effectiveness in accurately detecting strain variations and monitoring the tower's dynamic behavior under extreme wind loads. The findings support the implementation of condition-based maintenance strategies, enhance safety assessments, and enable early failure detection. This approach not only improves operational reliability but also facilitates timely intervention and maintenance during critical events. Received: 26 June 2025 | Revised: 12 September 2025 | Accepted: 11 November 2025 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement Data are available from the corresponding author upon reasonable request. Author Contribution Statement Yu Shi: Methodology, software, formal analysis, data curation, writing – original draft, writing – review & editing, visualization, supervision, and project administration. Abolghassem Zabihollah: Conceptualization, methodology, software, validation, investigation, resources, data curation, writing – original draft, writing – review & editing, visualization, supervision, and project administration. Yao-Chi Yu: Methodology, software, formal analysis, data curation, and writing – original draft. Arunima Pathak: Investigation, writing – original draft, and visualization. Oluwaseyi Oyetunji: Investigation.

Estimation of time dependent scour depth around circular bridge piers: Application of ensemble machine learning methods

Crack is a common cause of the degradation of concrete and may affect its structural durability. In order to ensure the bridge is safe utilized in anticipated period of their future service, a proper maintenance process and procedure should be taken. Therefore in this study, static load test were performed on a pre-tensioned (PRT) concrete beam to investigate crack behaviour before and after retrofitting process as well as to determine the effectiveness of the retrofitting method. A control beam named PRTB1 will fully loaded until fail to determine its maximum load capacity and critical load of the beam. Hence another beam named PRTB-FRP will be loaded until it reached it critical load capacity before retrofitted using Fiber Reinforced Polymer (FRP) plates located beneath the centre of the beam. After the retrofitting process PRTB-FRP will be put again under the static load. The load capacity of PRTB-FRP increased compared to PRTB1 with some improvement in crack propagation behaviour after retrofitted.

Accurate and fast prediction of sea ice conditions is the foundation of safety guarantee for Arctic navigation. Aiming at the imperious demand of short-term prediction for sea ice, we develop a new data-driven prediction technique for the sea ice concentration (SIC) combined with causal analysis. Through the causal analysis based on kernel Granger causality (KGC) test, key environmental factors affecting SIC are selected. Then multiple popular machine learning (ML) algorithms, namely self-adaptive differential extreme learning machine (SaD-ELM), classification and regression tree (CART), random forest (RF) and support vector regression (SVR), are employed to predict daily SIC, respectively. The experimental results in the Barents-Kara (B-K) sea show: (1) compared with correlation analysis, the input variables of ML models screened out by causal analysis achieve better prediction; (2) when lead time is short (<3 d), the four ML algorithms are all suitable for short-term prediction of daily SIC, while RF and SaD-ELM have better prediction performance with long lead time (>3 d); (3) RF has the best prediction accuracy and generalization ability but hugely time consuming, while SaD-ELM achieves more favorable performance when taking computational complexity into consideration. In summary, ML is applicable to short-term prediction of daily SIC, which develops a new way of sea ice prediction and provides technical support for Arctic navigation.

Ambient air quality monitoring requires low-cost environmental sensor devices that are affordable and feasible for large-scale implementation. However, issues such as sensor drift, environmental sensitivity, and inter-sensor variability affect data accuracy and cannot be adequately addressed by traditional calibration methods. This paper summarizes the use of machine learning techniques for calibrating low-cost sensors. The literature review shows that machine learning models like Random Forest, Support Vector Regression, and Neural Networks significantly improve sensor accuracy and reliability. For instance, Random Forest models reduced the root mean squared error by 30% for PM2.5 measurements, while Neural Networks achieved an R value of 0.997 for methane sensors. Integrating machine learning with IoT and mobile technologies enhances real-time monitoring and spatial resolution. Identified gaps include the quality of training datasets, managing environmental variability, and improving model transferability across different contexts. Addressing these gaps through advanced models and real-time calibration methodologies will further enhance sensor performance, ensuring more precise and reliable environmental data.

Efficient spare part management plays a crucial role in supporting operational continuity at PT. Setia Karya Transport (Great Giant Foods). The current spare part forecasting process is still reactive and relies on periodic evaluations, resulting in potential inefficiencies in procurement planning. This study aims to develop a machine learning-based predictive model to forecast spare part requirements using historical transaction data from January to July 2025. The research applied three modeling scenarios: (1) a hybrid model combining Support Vector Regression (SVR), Random Forest, and Statistical methods; (2) pure statistical methods with zero-ratio classification; and (3) the XGBoost algorithm with zero-ratio classification. Model performance was evaluated using Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) metrics. The results showed that the hybrid approach achieved the best performance with an MAE of 2.919 and an RMSE of 8.056, indicating higher prediction accuracy compared to other models. The findings demonstrate that integrating machine learning with statistical approaches can effectively enhance forecasting accuracy and support data-driven decision-making in warehouse management. Keywords : Machine Learning, Forecasting, Spare Part, Random Forest, Support Vector Regression

Integrating machine learning (ML) with nanophotonic engineering, this work achieves unprecedented performance in surface plasmon resonance (SPR) biosensing through a co-designed gold-coated photonic crystal fiber (PCF-SPR) sensor and multi-algorithm computational framework. An asymmetric circular PCF structure with concentric air-hole rings ([Formula: see text], [Formula: see text]) and a 50 nm gold layer maximizes evanescent field-analyte overlap, generating complex spectral signatures ideal for machine learning interpretation. High-fidelity COMSOL Multiphysics simulations produce 1560 synthetic data points across refractive indices (RIs) of 1.33-1.38, capturing confinement loss, wavelength sensitivity, and effective permittivity. Three regression models-Multiple Linear Regression (MLR), Support Vector Regression (SVR), and Random Forest Regression (RFR)-are rigorously evaluated for predicting optical responses. The sensor demonstrates a record wavelength sensitivity of 31 846.46 nm/RIU-1 at [Formula: see text], with minimal variation (0.02%) across the biological range, alongside a resolution of [Formula: see text] RIU. Crucially, MLR outperforms nonlinear counterparts, achieving superior accuracy in confinement loss (MAE = 3.97, RMSE = 5.03) and sensitivity prediction (MAE = 40.18, RMSE = 50.54). This synergy of optimized pure-gold microstructures and interpretable machine learning establishes a robust pipeline for high-sensitivity, noise-resilient biosensing, surpassing prior ML-enhanced plasmonic sensors in critical performance metrics while simplifying fabrication.