Lower Prediction Error Research Articles

Toward a physics-guided machine learning approach for predicting chaotic systems dynamics

Predicting the dynamics of chaotic systems is crucial across various practical domains, including the control of infectious diseases and responses to extreme weather events. Such predictions provide quantitative insights into the future behaviors of these complex systems, thereby guiding the decision-making and planning within the respective fields. Recently, data-driven approaches, renowned for their capacity to learn from empirical data, have been widely used to predict chaotic system dynamics. However, these methods rely solely on historical observations while ignoring the underlying mechanisms that govern the systems' behaviors. Consequently, they may perform well in short-term predictions by effectively fitting the data, but their ability to make accurate long-term predictions is limited. A critical challenge in modeling chaotic systems lies in their sensitivity to initial conditions; even a slight variation can lead to significant divergence in actual and predicted trajectories over a finite number of time steps. In this paper, we propose a novel Physics-Guided Learning (PGL) method, aiming at extending the scope of accurate forecasting as much as possible. The proposed method aims to synergize observational data with the governing physical laws of chaotic systems to predict the systems' future dynamics. Specifically, our method consists of three key elements: a data-driven component (DDC) that captures dynamic patterns and mapping functions from historical data; a physics-guided component (PGC) that leverages the governing principles of the system to inform and constrain the learning process; and a nonlinear learning component (NLC) that effectively synthesizes the outputs of both the data-driven and physics-guided components. Empirical validation on six dynamical systems, each exhibiting unique chaotic behaviors, demonstrates that PGL achieves lower prediction errors than existing benchmark predictive models. The results highlight the efficacy of our design of data-physics integration in improving the precision of chaotic system dynamics forecasts.

A Study on Canopy Volume Measurement Model for Fruit Tree Application Based on LiDAR Point Cloud

The accurate measurement of orchard canopy volume serves as a crucial foundation for wind regulation and dosage adjustments in precision orchard management. However, existing methods for measuring canopy volume fail to satisfy the high precision and real-time requirements necessary for accurate variable-rate applications in fruit orchards. To address these challenges, this study develops a canopy volume measurement model for orchard spraying using LiDAR point cloud data. In the domain of point cloud feature extraction, an improved Alpha Shape algorithm is proposed for extracting point cloud contours. This method improves the validity judgment for contour line segments, effectively reducing contour length errors on each 3D point cloud projection plane. Additionally, improvements to the mesh integral volume method incorporate the effects of canopy gaps in height difference calculations, significantly enhancing the accuracy of canopy volume estimation. For feature selection, a random forest-based recursive feature elimination method with cross-validation was employed to filter 10 features. Ultimately, five key features were retained for model training: the number of point clouds, the 2D point cloud contour along the X- and Z-projection directions, the 2D width in the Y-projection direction, and the 2D length in the Z-projection direction. During model construction, the study optimized the hyperparameters of partial least squares regression (PLSR), backpropagation (BP) neural networks, and gradient boosting decision trees (GBDT) to build canopy volume measurement models tailored to the dataset. Experimental results indicate that the PLSR model outperformed other approaches, achieving optimal performance with three principal components. The resulting canopy volume measurement model achieved an R2 of 0.9742, an RMSE of 0.1879, and an MAE of 0.1161. These results demonstrate that the PLSR model exhibits strong generalization ability, minimal prediction bias, and low average prediction error, offering a valuable reference for precision control of canopy spraying in orchards.

Targeted and untargeted cross-sectional study for sex-specific identification of plasma biomarkers of COVID-19 severity.

Coronavirus disease 2019 is a highly contagious respiratory illness caused by the coronavirus SARS-CoV-2. Symptoms can range from mild to severe and typically appear 2-14days after virus exposure. While vaccination has significantly reduced the incidence of severe complications, strategies for the identification of new biomarkers to assess disease severity remains a critical area of research. Severity biomarkers are essential for personalizing treatment strategies and improving patient outcomes. This study aimed to identify sex-specific biomarkers for COVID-19 severity in a Chilean population (n = 123 female, n = 115 male), categorized as control, mild, moderate, or severe. Data were collected using clinical biochemistry parameters and mass spectrometry-based metabolomics and lipidomics to detect alterations in plasma cytokines, metabolites, and lipid profiles related to disease severity. Principal component analysis (PCA) and orthogonal partial least squares discriminant analysis (OPLS-DA) were performed to select significant characteristic features for each group. The results revealed distinct biomarkers for males and females. In males, COVID-19 severity of was associated with inflammation parameters, triglycerides content, and phospholipids profiles. For females, liver damage parameters, triglycerides content, cholesterol derivatives, and phosphatidylcholine were identified as severity biomarkers. For both sexes, most of the biomarker combinations evaluated got areas under the ROC curve greater than 0.8 and low prediction errors. These findings suggest that sex-specific biomarkers can help differentiate the levels of COVID-19 severity, potentially aiding in the development of tailored treatment approaches.

Assessment of Piperacillin-Tazobactam Population Pharmacokinetic Models in Neonates: An External Validation.

Neonatal pharmacotherapy has gained attention from clinicians and regulatory agencies for optimizing the dosage of the drug which improves therapeutic outcomes in this special population. Piperacillin-tazobactam antibiotic is commonly used as a therapeutic option for treatment of severe infection in neonatal intensive care units. There are few population pharmacokinetic (PopPK) studies of piperacillin and tazobactam published for this specific population and which were not validated in other study settings. The aim of this study was to externally evaluate the published population pharmacokinetic models for piperacillin-tazobactam. A systematic review was conducted through Scopus, PubMed, and Embase databases to identify PopPK models. Clinical data collected in neonates treated with piperacillin-tazobactam were used for evaluation of these models. Various prediction-based metrics were used for assessing the bias and precision of PopPK models using individual predictions. Three PopPK models were identified for external evaluation. A total of 53 plasma samples were collected from 46 neonates admitted in the neonatal intensive care unit. The PopPK models reported by Cohen-Wolkowiez et al. for piperacillin and Li et al. for tazobactam were able to predict well for our clinical data. The PopPK models by Cohen-Wolkowiez et al. and Li et al. predicted our data well for piperacillin and tazobactam with the lower relative median absolute predictive error (rMAPE) of 8.61% and 16.48% and relative root mean square error (rRMSE) of 0.01 and 0.03, respectively. External evaluation of the published PopPK models of piperacillin and tazobactam resulted in enhancing their credibility to be implemented in clinical practice.

Comparison Between LSTM, GRU and VARIMA in Forecasting of Air Quality Time Series Data

Air quality forecast is essential in alerting the public, especially those who have respiratory diseases, to take necessary precautions beforehand. The public can be forewarned of any worsening of air quality and be aware of the importance of reducing air pollution. In recent years, forecasting techniques based on deep learning algorithms such as recurrent neural network (RNN) have seen improvements in both accuracy and execution speed. Long short-term memory (LSTM) network and gated recurrent unit (GRU) are among the most popular variants of RNN. In this study, the hourly PM2.5 concentrations at five selected air quality monitoring stations, provided by the Department of Environment Malaysia, are forecasted using LSTM, GRU and vector autoregressive integrated moving average (VARIMA) models respectively. Data containing missing, negative and zero values are pre-processed using an interpolation technique before being split into training and test sets on an 80:20 ratio basis. Optimal combinations of hyperparameter values are selected via manual tuning based on the 10-fold growing window cross-validation results. The model performance is evaluated based on RMSE, MAE and MAPE. The results demonstrate that neural network models significantly outperform the multivariate time series model in which the LSTM and GRU models have comparable performance in forecasting the hourly PM2.5 concentration, with a slightly better prediction in the west coast region for LSTM and the east coast region for GRU. However, due to the complex architecture of neural networks, the computational time to train both LSTM and GRU models is three times longer than that for VARIMA. Additionally, it is observed that a higher percentage of interpolated values leads to lower prediction errors.

Monitoring a Coffee Roasting Process Based on Near‐Infrared and Raman Spectroscopy Coupled With Chemometrics

ABSTRACTRoasting is a fundamental step in coffee processing, where complex reactions form chemical compounds related to the coffee flavor and its health‐beneficial effects. These reactions occur on various time scales depending on the roasting conditions. To monitor the process and ensure reproducibility, the study proposes simple and fast techniques based on spectroscopy. This work uses analytical tools based on near‐infrared (NIR) and Raman spectroscopy to monitor the coffee roasting process by predicting chemical changes in coffee beans during roasting. Green coffee beans of Robusta and Arabica species were roasted at 240°C for different roasting times. The spectra of the samples were taken using the spectrometers and modeled by the k‐nearest neighbor regression (KNR), partial least squares regression (PLSR), and multiple linear regression (MLR) to predict concentrations from the spectral data sets. For NIR spectra, all the models provided satisfactory results for the prediction of chlorogenic acid, trigonelline, and DPPH radical scavenging activity with low relative root mean square error of prediction (pRMSEP < 9.649%) and high coefficient of determination (R2 > 0.915). The predictions for ABTS radical scavenging activity were reasonably good. On the contrary, the models poorly predicted the caffeine and total phenolic content (TPC). Similarly, all the models based on the Raman spectra provided good prediction accuracies for monitoring the dynamics of chlorogenic acid, trigonelline, and DPPH radical scavenging activity (pRMSEP < 7.849% and R2 > 0.944). The results for ABTS radical scavenging activity, caffeine, and TPC were similar to those of NIR spectra. These findings demonstrate the potential of Raman and NIR spectroscopy methods in tracking chemical changes in coffee during roasting. By doing so, it may be possible to control the quality of coffee in terms of its aroma, flavor, and roast level.

The application of predictive stochastic model based on Monte Carlo method in building energy saving renovation

Abstract: This research has established an energy consumption prediction model based on the Monte Carlo method to resolve the energy-saving transformation problem. First, simplify the building to construct the proposed model. Second, through the principle of building energy balance and Monte Carlo method, the cooling and heat demand model of regional buildings and the energy consumption prediction model of regional buildings are built. Finally, the energy consumption simulation and energy consumption prediction of the regional building complex after energy-saving renovation are carried out. The experiment shows that the building energy consumption in July and August was relatively high, reaching 2.36E+14 and 2.4E+14, respectively. The energy consumption in April and November was relatively low, reaching 1.2E+14 and 1.4E+14, respectively. The highest prediction error was in November, reaching 12%. The lowest prediction error was in January and February, only about 2%. The error of monthly energy consumption predicted by Monte Carlo method is less than 12%, the Root-mean-square deviation is 5%, and the error between predicted and actual annual total energy consumption is only about 2%. By comparing the predicted energy consumption after energy-saving renovation with before, the energy-saving rate reached about 20%. The research results indicate that the proposed Monte Carlo based predictive stochastic model exhibits good predictive performance in building energy-saving renovation, providing theoretical guidance and reference for feasibility studies, planning, prediction, decision-making, and optimization of building energy-saving renovation.

A Hierarchical-Based Learning Approach for Multi-Action Intent Recognition.

Recent applications of wearable inertial measurement units (IMUs) for predicting human movement have often entailed estimating action-level (e.g., walking, running, jumping) and joint-level (e.g., ankle plantarflexion angle) motion. Although action-level or joint-level information is frequently the focus of movement intent prediction, contextual information is necessary for a more thorough approach to intent recognition. Therefore, a combination of action-level and joint-level information may offer a more comprehensive approach to predicting movement intent. In this study, we devised a novel hierarchical-based method combining action-level classification and subsequent joint-level regression to predict joint angles 100 ms into the future. K-nearest neighbors (KNN), bidirectional long short-term memory (BiLSTM), and temporal convolutional network (TCN) models were employed for action-level classification, and a random forest model trained on action-specific IMU data was used for joint-level prediction. A joint-level action-generic model trained on multiple actions (e.g., backward walking, kneeling down, kneeling up, running, and walking) was also used for predicting the joint angle. Compared with a hierarchical-based approach, the action-generic model had lower prediction error for backward walking, kneeling down, and kneeling up. Although the TCN and BiLSTM classifiers achieved classification accuracies of 89.87% and 89.30%, respectively, they did not surpass the performance of the action-generic random forest model when used in combination with an action-specific random forest model. This may have been because the action-generic approach was trained on more data from multiple actions. This study demonstrates the advantage of leveraging large, disparate data sources over a hierarchical-based approach for joint-level prediction. Moreover, it demonstrates the efficacy of an IMU-driven, task-agnostic model in predicting future joint angles across multiple actions.

COMPARATIVE ANALYSIS OF TRIANGULAR FUZZY HIDDEN MARKOV MODELS AND TRADITIONAL HIDDEN MARKOV MODELS

This study optimizes Traditional Hidden Markov Models (THMMs) using Triangular Fuzzy Membership Functions, resulting in Triangular Fuzzy Hidden Markov Models (TFHMMs) that tolerate ambiguous observations and gradual state transitions in agricultural data prediction. Using oilseed area data from 1992 to 2022, we compare TFHMMs to traditional HMMs, focusing on predicting accuracy using the Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC), Corrected Akaike Information Criterion (AICc), and Hannan-Quinn Information Criterion (HQIC). Our research includes stationary parameters to improve model stability and uses the Viterbi technique to find optimal state sequences, which improves forecast interpretability. The results show that THMMs outperform TFHMMs at capturing the complicated patterns of agricultural data, with lower prediction errors and more reliability. This work emphasizes the potential of fuzzy logic in not improving probabilistic models for agricultural forecasting, providing a more delicate and accurate approach to analyzing and predicting agricultural trends.

Proprioceptive and Exteroceptive Information Perception in a Fabric Soft Robotic Arm via Physical Reservoir Computing with Minimal Training Data

Over recent decades, soft and reconfigurable robots have rapidly emerged thanks to their ability to interact safely with humans and adapt to complex environments. . However, their softness makes accurate control challenging, requiring high‐fidelity sensing for posture and contact estimation.Traditional camera‐based sensors and load cells have limited portability and accuracy, and they will inevitably increase the robot's cost and weight. In this study, instead of using specialized sensors, only distributed pressure data inside a pneumatics‐driven soft arm are collected and the physical reservoir computing principle is applied to simultaneously predict its kinematic posture (i.e., bending angle) and payload status (i.e., payload mass). Results show that, with careful readout training, one can obtain accurate bending angle and payload mass predictions via simple, weighted linear summations of pressure readings. In addition,analysis show that, to guarantee low prediction errors within 10%, bending angle prediction requires less training data than payload prediction. This reveals that balanced linear and nonlinear body dynamics are critical for the physical reservoir to accomplish complex proprioceptive and exteroceptive information perception tasks. Finally, the method of exploring efficient readout training methods presented here could be extended to other soft robotic systems to maximize their perception capabilities.

Multistep photovoltaic power forecasting based on multi-timescale fluctuation aggregation attention mechanism and contrastive learning

The integration of photovoltaic (PV) power into electrical grids introduces significant uncertainty due to the inherent volatility and intermittency of solar energy, underscoring the need for precise short and medium-term PV power forecasting. Despite the superior performance of Transformer-based time series methods, their application to PV power prediction remains suboptimal. In response to this deficiency, this paper proposes a novel attention mechanism that aggregates fluctuations across multiple time scales. This mechanism enhances the segmentation and extraction of nonlinear correlations between PV power outputs and meteorological factors, assigning variable weights to patterns of change across different time scales. Furthermore, a novel approach for selecting similar days is also developed based on contrastive learning, which enables self-supervised identification of similarities among PV power samples and enhances the model’s attention to local dynamic variations. Comparative analysis with eight state-of-the-art benchmark methods shows that the proposed MFA-attention model achieves lower prediction errors and improved effectiveness.© 2017 Elsevier Inc. All rights reserved.

Tool Wear Prediction in Machining of Aluminum Matrix Composites with the Use of Machine Learning Models.

This paper discusses the diagnostic models of tool wear during face milling of Aluminum Matrix Composite (AMC), classified as a difficult-to-cut material. Prediction and classification models were considered. The models were based on one-dimensional simple regression or on multidimensional regression trees, random forest, nearest neighbor and multilayer perceptron neural networks. Measures of diagnostic signals obtained from measurements of cutting forces and vibration accelerations of the workpiece were used. The study demonstrated that multidimensional models outperformed one-dimensional models in terms of prediction accuracy and classification performance. Specifically, multidimensional predictive models exhibited lower maximum and average absolute prediction errors (0.036 mm vs. 0.050 mm and 0.026 mm vs. 0.045 mm, respectively), and classification models recorded fewer Type I and Type II errors. Despite the increased complexity, the higher predictive accuracy (up to 0.97) achieved with multidimensional models was shown to be suitable for industrial applications. However, simpler one-dimensional models offered the ad-vantage of greater reliability in signal acquisition and processing. It was also highlighted that the advantage of simple models from a practical point of view is the reduced complexity and consequent greater reliability of the system for acquiring and processing diagnostic signals.

Federated Learning‐Based Mobile Traffic Prediction in Satellite‐Terrestrial Integrated Networks

ABSTRACTIntroductionWith the development and integration of satellite and terrestrial networks, mobile traffic prediction has become more important than before, which is the basis for service provision and resource scheduling when supporting various vertical applications. However, existing traffic prediction methods, especially deep learning‐based methods, require massive data for model training. Due to data privacy concerns, mobile traffic data are not easily shared among different parties, making it difficult to obtain a precise prediction model.MethodsTo mitigate the data leakage risk, a federated learning framework is proposed in this study for mobile traffic prediction in satellite‐terrestrial integrated networks to achieve a tradeoff between data privacy and prediction accuracy. In the proposed framework, local models are trained in base stations on the ground, and a global model is aggregated in the satellite edge server in space.ResultsA deep learning‐based prediction model with an adaptive graph convolutional network (AGCN) and long short‐term memory (LSTM) modules is proposed and validated in numerical experiments, which achieves the lowest prediction error with a real‐world traffic dataset when compared with other graph neural network (GNN) variants in the federated learning setting.ConclusionNumerical experiments with a real‐world mobile traffic dataset demonstrate the effectiveness of the proposed approach, which outperforms other GNN variants with lower prediction errors.

A new multivariate blood glucose prediction method with hybrid feature clustering and online transfer learning.

Accurate blood glucose (BG) prediction is greatly benefit for the treatment of diabetes. Generally, clinical physicians are required to comprehensively analyze various factors, such as patient's body temperature, meal, sleep, insulin injection, continuous glucose monitoring (CGM), and other information, to evaluate the fluctuation trend of blood glucose. To address this problem, this paper proposes a multivariate blood glucose prediction method based on mixed feature clustering. It clusters time series data with diverse or mixed features related to blood glucose, effectively leveraging correlations and distribution characteristics. By combining incremental clustering of multivariate time series with transfer learning, this method achieves online prediction of blood glucose levels. The experimental results indicate that the proposed method can decrease the prediction error RMSE by 4.2% (PH=30min) and 5.9% (PH=60min). Compared with other prediction methods, the training time of the multivariate prediction method is reduced by 5.2% (PH=30min) and 4.7% (PH=60min). It was also validated and compared with other methods in a real dataset. The proposed method in this study has lower prediction error and better prediction performance in the prediction horizon(PH) of PH=30, 45, 60, 75, and 90min, respectively. Compared with the traditional unitary and multivariate time series prediction method, the approach proposed in this paper significantly improves the accuracy and robustness of blood glucose prediction. According to the evaluation results on the data set from OhioT1DM and the Sixth People's Hospital of Shanghai, the proposed method has better generalization performance and clinical acceptability.

Evaluate Multi-Objective Optimization Model for Product Supply Chain Inventory Control Based on Grey Wolf Algorithm

Enterprise supply chain inventory control plays a critical role in modern enterprise management. Yet achieving multi-objective optimization remains challenging. This paper proposes a deep learning integrated model based on grey wolf optimization (GWO-DLIM) aimed at optimizing inventory holding costs, stockout costs, and order costs. The model integrates multi-layer perceptron (MLP), DeBERTa, and GWO, leveraging the powerful predictive and feature extraction capabilities of deep learning models, combined with the global optimization ability of the grey wolf algorithm, to achieve multi-objective optimization. These results demonstrate that the GWO-DLIM model significantly outperforms other comparative models across all metrics, exhibiting lower prediction errors and root mean square errors, as well as higher service levels. This study provides an effective multi-objective optimization solution for supply chain inventory management, holding significant theoretical and practical implications.

IGGCN: Individual-guided graph convolution network for pedestrian trajectory prediction

Accurately predicting the future trajectory of pedestrians is crucial for applications such as autonomous driving and robot navigation. Graph convolution is widely used in trajectory prediction tasks due to its scalability and adaptive feature-learning capabilities. However, there are two problems with pedestrian trajectory prediction methods based on graph convolution: 1. Previous methods struggled to adjust social interactions according to the attributes of different pedestrians, making it difficult to accurately model the relative importance between different pedestrians and others; 2. Previous methods lacked dynamic processing of pedestrian spatial-temporal interaction features to capture high-level spatial-temporal interaction features effectively. Therefore, we propose an Individual-Guided Graph Convolution Network (IGGCN) for pedestrian trajectory prediction. To tackle problem 1, we design an individual-guided interaction module that can adjust pedestrian social interaction modeling according to the pedestrian's attributes, thereby achieving an accurate description of the relative importance of pedestrians. We extend the module to temporal interaction modeling to further achieve an accurate description of the relative importance of time frames. To address problem 2, we design a deformable convolution module to dynamically process spatial-temporal interaction features through deformable convolution kernels, facilitating the capture of high-level spatial-temporal interaction features. We evaluate our method on the ETH, UCY, and SDD datasets. Quantitative analysis shows that our method has lower prediction errors than the current state-of-the-art methods. Qualitative analysis further reveals that our method effectively eliminates the influence of irrelevant pedestrians and accurately models the spatial-temporal interaction relationship of pedestrians.

EXPRESS: A Framework for Execution Time Prediction of Concurrent CNNs on Xilinx DPU Accelerator

Deep learning Processor Unit (DPU) is a highly configurable CNN accelerator that supports a variety of CNNs and can be implemented with multiple instances on the same FPGA. Many applications deploy concurrent execution of different CNNs and in such a setting, an execution time predictor can help “optimize” the DPU configurations to meet the performance requirements of different tasks. We characterize CNN execution on DPUs and reduce the variability in execution time due to interference from the operating system. Subsequently, we propose a machine learning-based framework (EXPRESS) to predict the execution time of any given CNN on a DPU configuration, considering CNN, DPU, and bus characteristics. We improvise EXPRESS to support heterogeneous CNNs in EXPRESS-2.0 by making features independent of the number of CNNs. Our entire experimentation is based on data from a real FPGA board for 16 standard CNNs. Our frameworks, EXPRESS and EXPRESS-2.0, significantly outperform state-of-the-art by achieving an average execution time prediction error of 2.2% and 0.7%, respectively. We illustrate the effectiveness of this low prediction error for design space exploration, which is very useful for embedded system application developers.

A Multitask Network Robustness Analysis System Based on the Graph Isomorphism Network.

Despite various measures across different engineering and social systems, network robustness remains crucial for resisting random faults and malicious attacks. In this study, robustness refers to the ability of a network to maintain its functionality after a part of the network has failed. Existing methods assess network robustness using attack simulations, spectral measures, or deep neural networks (DNNs), which return a single metric as a result. Evaluating network robustness is technically challenging, while evaluating a single metric is practically insufficient. This article proposes a multitask analysis system based on the graph isomorphism network (GIN) model, abbreviated as GIN-MAS. First, a destruction-based robustness metric is formulated using the destruction threshold of the examined network. A multitask learning approach is taken to learn the network robustness metrics, including connectivity robustness, controllability robustness, destruction threshold, and the maximum number of connected components. Then, a five-layer GIN is constructed for evaluating the aforementioned four robustness metrics simultaneously. Finally, extensive experimental studies reveal that 1) GIN-MAS outperforms nine other methods, including three state-of-the-art convolutional neural network (CNN)-based robustness evaluators, with lower prediction errors for both known and unknown datasets from various directed and undirected, synthetic, and real-world networks; 2) the multitask learning scheme is not only capable of handling multiple tasks simultaneously but more importantly it enables the parameter and knowledge sharing across tasks, thus preventing overfitting and enhancing the performances; and 3) GIN-MAS performs multitasks significantly faster than other single-task evaluators. The excellent performance of GIN-MAS suggests that more powerful DNNs have great potentials for analyzing more complicated and comprehensive robustness evaluation tasks.

A dual-stream temporal convolutional network for remaining useful life prediction of rolling bearings

Abstract Remaining useful life (RUL) prediction plays an indispensable role in the reliable operation and improved maintenance of rolling bearings. Currently, data-driven methods based on deep learning have made significant progress in RUL prediction. However, most of such methods only consider the correlation between channels, ignoring the importance of different time steps for RUL prediction. In addition, it is still challenging to effectively fuse the degradation features of rolling bearings to improve the model RUL prediction performance. To address the above issues, this paper proposes a novel data-driven RUL prediction method named dual-stream temporal convolution network (DSTCN). First, a hybrid attention temporal convolution block (HATCB) is designed to capture the correlation of degraded features on the channel dimension and temporal dimension. Second, a one-dimensional attention fusion module is designed. This module is capable of weight recalibration and assignment to adaptively fuse different degraded features. Afterward, the Hilbert Marginal spectrum is obtained using the Hilbert Huang Transform and used as the input to one stream. Meanwhile, vibration signals are used as the input of the other stream, thus building a dual-stream temporal convolution network to realize RUL prediction. The effectiveness of the proposed method is validated with two life-cycle datasets, and the results show that the method has lower prediction error than other methods for RUL prediction and prognostic analysis.

Raman spectroscopy coupled with the PLSR model: A rapid method for analyzing gamma-oryzanol content in rice bran oil

Rice bran oil (RBO) is widely used in food, nutraceutical, and cosmetic industries, due to its γ-oryzanol content, a key quality indicator. This study developed a rapid, non-destructive method for quantifying γ-oryzanol in RBO using Raman spectroscopy combined with partial least squares regression (PLSR). The optimal PLSR model, based on orthogonal signal correction (OSC)-pretreated data of Raman spectra from 800 to 1800 cm−1, demonstrated high accuracy with a strong R2-Pearson correlation coefficient of 0.9827 and low root mean square error of prediction (RMSEP) of 0.5314. Principal component analysis (PCA) of OSC-pretreated data showed improved sample grouping by concentration of γ-oryzanol compared to untreated data. Additionally, Bland-Altman plots comparing results from Raman and HPLC methods showed random scatter within ±2 SD of the mean difference, confirming the method's reliability. This study indicates that Raman spectroscopy can serve as a reliable method for determining γ-oryzanol content in RBO products within the related industries.