Prediction Error Research Articles

Advances in predicting surface shape changes of mirror blanks through elliptical nozzle gas jet forming

To facilitate the formation of bifocal aspheric optical surfaces, we present an approach for predicting the surface profile of bifocal aspheric surfaces formed by the gas-liquid interface when an elliptical nozzle gas jet is employed. Through an analysis of the gas flow field morphology emanating from the elliptical nozzle, we inferred the impact of gas jet parameters on the gas-liquid interface surface shape within the core region of the gas jet. By analyzing the variation in the gas flow field morphology emitted from an elliptical nozzle, we deduced the influence patterns of gas jet parameters on the gas-liquid interface surface shape within the gas jet's core region. Theoretical analysis is substantiated by numerical simulations, confirming regular changes in the vertex curvature and conic constant of mirror blanks concerning variations in jet initial velocity and nozzle aspect ratio. A comparison between experimental data and numerical simulation results reveals an average prediction deviation of 0.0083 mm−1 for the vertex curvature and a prediction deviation of 10.7 % for the conic constant, challenging to rectify within numerical simulations. Hence, an empirical model, incorporating jet parameters, is developed based on experimental data to predict the vertex curvature and conic constant of mirror blanks. This model demonstrates an average prediction error of 2.901 × 10−3 mm−1 for the vertex curvature and 7.64 % for the conic constant, surpassing the predictive accuracy of the numerical simulation model.

Attenuated total reflection Fourier transform infrared spectroscopy (ATR-FTIR) analysis of human nails: Implications for age determination in forensics.

A person's age estimation from biological evidence is a crucial aspect of forensic investigations, aiding in victim identification and criminal profiling. In this study, we present a novel approach of utilizing Attenuated Total Reflection Fourier Transform Infrared (ATR FT-IR) spectroscopy to predict the age of donors based on nail samples. A diverse dataset comprising nails from donors spanning different age groups was analyzed using ATR FT-IR, with subsequent multivariate analysis techniques used for age prediction. The developed partial least squares regression (PLS-R) model demonstrated promising accuracy in age estimation, with a root mean square error of prediction (RMSEP) equal to 11.1 during external validation. Additionally, a partial least squares discriminant analysis (PLS-DA) classification model achieved high accuracy of 88% in classifying donors into younger and older age groups during external validation. This proof-of-concept study highlights the potential of ATR FT-IR spectroscopy as a non-destructive and efficient tool for age estimation in forensic investigations, offering a new approach to forensic analysis with practical implications.

Intelligent prediction of surface roughness of PSZ ceramic grinding based on correlation analysis and CNN-BiLSTM neural network

Partially stabilized zirconia (PSZ) ceramics are widely used in aerospace industry and other fields due to their superior performance. Surface roughness is a key indicator for evaluating the grinding level of PSZ ceramics. In order to reduce the prediction error of grinding surface roughness, an acoustic emission prediction model for PSZ ceramic grinding surface roughness based on correlation analysis and convolution-bidirectional long short term memory neural network (CNN-BiLSTM) was proposed. By analyzing the correlation between the eigenvalues of grinding acoustic emission signals and the grinding surface roughness values, the most relevant frequency bands and feature matrices between the grinding acoustic emission signals and the grinding surface roughness were selected as the input parameters of the CNN-BiLSTM neural network to reduce the error of acoustic emission prediction of grinding surface roughness. The research results show that the average prediction error of PSZ ceramic grinding surface roughness based on correlation analysis and CNN-BiLSTM neural network is less than 3.92%.

Nutritional composition analysis in food images: an innovative Swin Transformer approach.

Accurate recognition of nutritional components in food is crucial for dietary management and health monitoring. Current methods often rely on traditional chemical analysis techniques, which are time-consuming, require destructive sampling, and are not suitable for large-scale or real-time applications. Therefore, there is a pressing need for efficient, non-destructive, and accurate methods to identify and quantify nutrients in food. In this study, we propose a novel deep learning model that integrates EfficientNet, Swin Transformer, and Feature Pyramid Network (FPN) to enhance the accuracy and efficiency of food nutrient recognition. Our model combines the strengths of EfficientNet for feature extraction, Swin Transformer for capturing long-range dependencies, and FPN for multi-scale feature fusion. Experimental results demonstrate that our model significantly outperforms existing methods. On the Nutrition5k dataset, it achieves a Top-1 accuracy of 79.50% and a Mean Absolute Percentage Error (MAPE) for calorie prediction of 14.72%. On the ChinaMartFood109 dataset, the model achieves a Top-1 accuracy of 80.25% and a calorie MAPE of 15.21%. These results highlight the model's robustness and adaptability across diverse food images, providing a reliable and efficient tool for rapid, non-destructive nutrient detection. This advancement supports better dietary management and enhances the understanding of food nutrition, potentially leading to more effective health monitoring applications.

Multiple Criteria-Based Intelligent Techniques for Efficient Handover in Next-Generation Networks

Background: Several wireless technologies are assumed to be operating in cooperation for next-generation networks. These networks offer various services to mobile users; however, efficient handover between different networks is the most challenging task in high mobility scenarios. The traditional signal strength-based handover algorithms are not able to cope with mobile users' high-quality requirements. Methods: In this paper, multiple criteria-based intelligent techniques are proposed to deal with inefficiencies related to handover. This technique makes use of artificial neural networks that take multiple parameters as inputs in order to predict the degradation of parameters. These predictions are further used to design rules for initiating handover procedures prior to service quality degradation. Results: Based on the prediction results obtained by deep neural networks, the handover decisions are recommended according to the type of application: conversational or streaming. Conclusion: The simulation results demonstrate the efficacy of the proposed method as there is an improvement of up to 40% and 25% in terms of handover rate and service disruption time, respectively, with an acceptable prediction error of 0.05.

TrafficPro: A road speed prediction framework for urban signal-controlled road networks

In view of the problem that traditional deep learning models do not consider the active time-varying characteristics of traffic flow (signal control information) when predicting the speed of urban road networks, and have low prediction accuracy, this paper proposes a speed prediction framework based on generative adversarial networks and graph neural networks. In this framework, the generator network simultaneously encodes the road network traffic flow and signal control information through active and passive prediction modules to generate prediction results, and then uses the discriminator network to improve the generalization of the prediction results. This framework can obtain higher prediction accuracy than traditional time series models and deep learning models. In the real road network speed prediction scenario, this framework can reduce the prediction error compared to the best benchmark model 3%-4%.

Early quality prediction of complex double-walled hollow turbine blades based on improved whale optimization algorithm

Abstract The precision in forming complex double-walled hollow turbine blades significantly influences their cooling efficiency, making the selection of appropriate casting process parameters critical for achieving fine-casting blade formation. However, the high cost associated with real blade casting necessitates strategies to enhance product formation rates and mitigate cost losses stemming from the overshoot phenomenon. To address this challenge, we propose a machine-learning (ML) data-driven framework leveraging an enhanced whale optimization algorithm (WOA) to estimate product formation under diverse process conditions. Complex double-walled hollow turbine blades serve as a representative case within our proposed framework. We constructed a database using simulation data, employed feature engineering to identify crucial features and streamline inputs, and utilized a whale optimization algorithm-back-propagation neural network (WOA-BP) as the foundational ML model. To enhance WOA-BP's performance, we introduce an optimization algorithm, ICWOA-BP, incorporating cubic chaotic mapping adaptation. Experimental evaluation of ICWOA-BP demonstrated an average mean absolute error (MAE) of 0.001995 mm, reflecting a 36.21% reduction in prediction error compared to conventional models, as well as two well-known optimization algorithms (PSO, QANA). Consequently, ICWOA-BP emerges as an effective tool for early prediction of dimensional quality in complex double-walled hollow turbine blades.

PREDICTION INDONESIA COMPOSITE INDEX USING INTEGRATION DECOMPOSITION- NEURAL NETWORK ENSEMBLE DURING VUCA ERA

The Volatility, Uncertainty, Complexity, and Ambiguity (VUCA) era causes turmoil in the capital markets, stocks, commodities, etc. The impact is a decline in the Composite Stock Price Index (IHSG) in 2020. Therefore, future data is needed to inform investors and business people when making portfolio decisions. This paper develops a decomposition and Neural Network (NN) integration model to predict ICI during the VUCA era. The results are presented empirically to show the model's effectiveness in reducing prediction errors. First, the actual data is converted into three components; second, with the Neural Network Ensemble (NNE) approach where the initial step of decomposition results is trained using artificial NN with architecture, training data, and topology to produce individual networks; The output is selected using Principal Component Analysis (PCA) and becomes input to the ensemble model, then combined using a simple average and weighted average. The empirical results from ICI predictions illustrate: (1) decomposition has the potential to overcome data that is characterized by high volatility; (2) NNE is able to reduce errors (MSE≤0.100e-4, MAE≤0.01) compared to individual networks (MSE=0.0024 MAE=0.0376); (3) ensemble combinations using weighted averages (MSE≤3.00e-5,MAE≤0.002) are superior to simple averages (MSE≤5.00e-5,MAE≤0.01); (4) the integration carried out shows effectiveness in predicting ICI and provides better prediction results.

Dopamine release plateau and outcome signals in dorsal striatum contrast with classic reinforcement learning formulations

We recorded dopamine release signals in centromedial and centrolateral sectors of the striatum as mice learned consecutive versions of visual cue-outcome conditioning tasks. Dopamine release responses differed for the centromedial and centrolateral sites. In neither sector could these be accounted for by classic reinforcement learning alone as classically applied to the activity of nigral dopamine-containing neurons. Medially, cue responses ranged from initial sharp peaks to modulated plateau responses; outcome (reward) responses during cue conditioning were minimal or, initially, negative. At centrolateral sites, by contrast, strong, transient dopamine release responses occurred at both cue and outcome. Prolonged, plateau release responses to cues emerged in both regions when discriminative behavioral responses became required. At most sites, we found no evidence for a transition from outcome signaling to cue signaling, a hallmark of temporal difference reinforcement learning as applied to midbrain dopaminergic neuronal activity. These findings delineate a reshaping of striatal dopamine release activity during learning and suggest that current views of reward prediction error encoding need review to accommodate distinct learning-related spatial and temporal patterns of striatal dopamine release in the dorsal striatum.

Response-Aided Score-Matching Representative Approaches for Big Data Analysis and Model Selection under Generalized Linear Models

In this paper, we propose an efficient method called the response-aided score-matching representative (RASMR) approach to facilitate massive data model selection and data analysis with generalized linear models (GLMs) and a predetermined data partition due to data localization. Similar to the original score-matching representative (SMR) approach, RASMR constructs an artificial data point, called the representative, for each data block. It then fits a GLM on the representative dataset, which provides not only an efficient approach for massive data analysis but also an ideal solution in response to privacy concerns by avoiding the transfer of sensitive data. By further splitting the data blocks according to the values of the response variables, RASMR can obtain more accurate parameter estimates than SMR. Furthermore, by theoretical justifications and simulation studies, we show that RASMR can be more efficiently utilized for model selection and variable selection for a massive dataset by approximating the Akaike information criterion (AIC) and the aggregated prediction errors for cross-validation, which are commonly used for choosing the most appropriate statistical model and drawing reliable conclusions. We also apply the proposed RASMR approach to the airline on-time performance data, which consists of 371 data files labeled by month, and show that RASMR can be successfully used for selecting the most appropriate model for real massive data analysis.

Probabilistic Tide Calculation for Multi-Wind Farm Distribution Network Based on CATTSTS Model

Traditional probabilistic tide calculation methods often fall short in capturing the dynamic nature of these systems, leading to discrepancies between calculated and actual data. To address this, a dynamic probabilistic tide calculation model is proposed in this study, incorporating a wind farm probabilistic model enhanced by the CATTSTS model. This integration aims to optimize prediction accuracy by improving feature focusing and data fitting, thereby reducing prediction errors and providing more reliable data for power system adjustments and optimizations. Experimental results demonstrate that the model's predictions for wind speed series in multi-wind farm distribution networks closely match actual conditions, underscoring its practical applicability and reliability in real-world settings. Furthermore, the study highlights the impact of spatial and temporal correlations on model performance. This research contributes to advancing the management of renewable energy integration in power systems, offering insights for more informed decision-making and operational efficiency.

DNA methylation clocks struggle to distinguish inflammaging from healthy aging, but feature rectification improves coherence and enhances detection of inflammaging.

There is no apparent biological significance of the CpGs selected by first- and next-generation clocksThe range of residuals for first- and next-generation clock predications on healthy samples is very large; for all models tested, a prediction error of +/-10-20 years is within the 95% range of variation for healthy controls and does not signify age accelerationThere is no significant shift in the mean of residuals for patient populations relative to healthy populations for most studied first- and next-generation clocks. For those with significance, the effect size is very small.Hypothesis-driven feature pre-selection, coupled with modified forward step-wise selection yields age predictors on par with first and next-generation clocks. EN/ML is not needed.Disease-related shifts at different CpG probes, along with learned model weights, can be either positive or negative; their combination leads to de-coherence effect in linear models.Model coherence can be induced by rectifying features to have only positive shifts in patient samples; this provides a better resolution between health and disease in DNAm age models, and expectedly, introduces more non-linearity to the input data.

Prediction errors lead to updating of memories for conversations

ABSTRACT Previous research has established that the brain uses episodic memories to make continuous predictions about the world and that prediction errors, so the mismatch between generated predictions and reality, can lead to memory updating. However, it remains unclear whether prediction errors can stimulate updating in memories for naturalistic conversations. Participants encoded naturalistic dialogues, which were later presented in a modified form. We found that larger modifications were associated with increased learning of the modified statement. Moreover, memory for the original version of the statement was weakened after medium-strong prediction errors, which resulted from the interplay of modification extent and strength of previous memory. After strong prediction errors, both original and modification were well-remembered. Prediction errors thus play a role in keeping representations of statements and therefore socially relevant knowledge about others up to date.

Reward-driven cerebellar climbing fiber activity influences both neural and behavioral learning.

The cerebellum plays a key role in motor coordination and learning. In contrast with classical supervised learning models, recent work has revealed that CFs can signal reward-predictive information in some behaviors. This raises the question of whether CFs may also operate according to principles similar to those described by reinforcement learning models. To test how CFs operate during reward-guided behavior, and evaluate the role of reward-related CF activity in learning, we have measured CF responses in Purkinje cells of the lateral cerebellum during a Pavlovian task using 2-photon calcium imaging. Specifically, we have performed multi-stimulus experiments to determine whether CF activity meets the requirements of a reward prediction error (rPE) signal for transfer from an unexpected reward to a reward-predictive cue. We find that once CF activity is transferred to a conditioned stimulus, and there is no longer a response to reward, CFs cannot generate learned responses to a second conditioned stimulus that carries the same reward prediction. In addition, by expressing the inhibitory opsin GtACR2 in neurons of the inferior olive, and optically inhibiting these neurons across behavioral training at the time of unexpected reward, we find that the transfer of CF signals to the conditioned stimulus is impaired. Moreover, this optogenetic inhibition also impairs learning, resulting in a deficit in anticipatory lick timing. Together, these results indicate that CF signals can exhibit several characteristics in common with rPEs during reinforcement learning, and that the cerebellum can harness these learning signals to generate accurately timed motor behavior.

Stochastic Parameterization of Moist Physics Using Probabilistic Diffusion Model

Deep-learning-based convection schemes have garnered significant attention for their notable improvements in simulating precipitation distribution and tropical convection in Earth system models. However, these schemes struggle to capture the stochastic nature of moist physics, which can degrade the simulation of large-scale circulations, climate means, and variability. To address this issue, a stochastic parameterization scheme called DIFF-MP, based on a probabilistic diffusion model, is developed. Cloud-resolving data are coarse-grained into resolved-scale variables and subgrid contributions, which serve as conditional inputs and outputs for DIFF-MP. The performance of DIFF-MP is compared with that of generative adversarial networks and variational autoencoders. The results demonstrate that DIFF-MP consistently outperforms these models in terms of prediction error, coverage ratio, and spread–skill correlation. Furthermore, the standard deviation, skewness, and kurtosis of the subgrid contributions generated by DIFF-MP more closely match the test data than those produced by the other models. Interpretability experiments confirm that DIFF-MP’s parameterization of moist physics is physically consistent.

Protecting Infinite Data Streams from Wearable Devices with Local Differential Privacy Techniques

The real-time data collected by wearable devices enables personalized health management and supports public health monitoring. However, sharing these data with third-party organizations introduces significant privacy risks. As a result, protecting and securely sharing wearable device data has become a critical concern. This paper proposes a local differential privacy-preserving algorithm designed for continuous data streams generated by wearable devices. Initially, the data stream is sampled at key points to avoid prematurely exhausting the privacy budget. Then, an adaptive allocation of the privacy budget at these points enhances privacy protection for sensitive data. Additionally, the optimized square wave (SW) mechanism introduces perturbations to the sampled points. Afterward, the Kalman filter algorithm is applied to maintain data flow patterns and reduce prediction errors. Experimental validation using two real datasets demonstrates that, under comparable conditions, this approach provides higher data availability than existing privacy protection methods for continuous data streams.

Short-Term Prediction of Origin–Destination Passenger Flow in Urban Rail Transit Systems with Multi-Source Data: A Deep Learning Method Fusing High-Dimensional Features

Short-term origin–destination (OD) passenger flow forecasting is crucial for urban rail transit enterprises aiming to optimise transportation products and increase operating income. As there are large-scale OD pairs in an urban rail transit system, OD passenger flow cannot be obtained in real time (temporal hysteresis). Additionally, the distribution characteristics are also complex. Previous studies mainly focus on passenger flow prediction at metro stations, while few methods solve the OD passenger flow prediction problems of an urban rail transit system. In view of this, we propose a novel deep learning method fusing high-dimensional features (HDF-DL) with multi-source data. The HDF-DL method is combined with three modules. The temporal module incorporates the time-varying, trend, and cyclic characteristics of OD passenger flow, while the latest OD passenger flow time sequence (within 1 h) is excluded from the time-varying characteristics. In the spatial module, the K-means and K-shape algorithms are used to classify OD pairs from multiple perspectives and capture the spatial features, reducing the difficulty of OD passenger flow predictions with large-scale and complex characteristics. Weather factors are considered in the external feature module. The HDF-DL method is tested on a large-scale metro system in China, in which eight baseline models are designed. The results show that the HDF-DL method achieves high prediction accuracy across multiple time granularities, with a mean absolute percentage error of about 10%. OD passenger flow in every departure time interval can be predicted with high and stable accuracy, effectively capturing temporal characteristics. The modular design of HDF-DL, which fuses high-dimensional features and employs appropriate neural networks for different data types, significantly reduces prediction errors and outperforms baseline models.

Detection of piperine content in black pepper using a molecular imprinted poly(N,N-dimethylacrylamide) embedded graphite electrode: A machine learning based prediction approach

The paper presents a molecular imprinted graphite electrode for selective and sensitive detection of piperine (1-Propylpiperidine) in Piper nigrum (black pepper). Poly(N,N-dimethylacrylamide) (PDMAM) was utilized as a functional monomer directing polymerization of uniform molecularly imprinted polymer (MIP) layers on the surface of the graphite layer using ethylene glycol dimethacrylate (EGDMA) as cross-linker with piperine (PIP) as template molecules. The formation of imprinting, non-imprinting, and elution of analytes within the polymer matrix were studied by field emission scanning electron microscope (FESEM), Fourier transform infrared (FTIR), UV–visible (UV–Vis) and X-ray photoelectron spectroscopy (XPS). The electrochemical response of piperine was evaluated through differential pulse voltammetry (DPV) using a PDMAM-MIP@G electrode that showed an oxidation peak at 1.25 ± 0.15 V. Under optimized experimental conditions, DPV peak currents were linear over two concentration ranges (0.001–1 µM and 1–200 µM). A limit of detection (LOD) was found to be 0.0006 µM. Developed electrode yielded high selectivity, sensitivity (12.92 µA/µM (lower linear range) and 0.33 µA/µM (upper linear range)), promising reproducibility, long-term stability (3.85 % decrease in response over 28 days), and interference immunity. The developed PDMAM-MIP@G electrode was applied to real samples using four branded pepper powder procured from local market and the sensor data was recorded. A convolutional neural network (CNN) driven prediction model has been proposed to predict the piperine concentration. Among the four CNN models tested, the best model, averaged over 50 runs, achieved a mean absolute error (MAE) of 0.268, a mean prediction error of 2.35 %, and a R-squared value of 0.93 on the testing set when compared with reference values obtained from reverse-phase high-performance liquid chromatography (RP-HPLC).

Cerebellar climbing fibers signal flexible, rapidly adapting reward predictions.

Classical models of cerebellar computation posit that climbing fibers (CFs) operate according to supervised learning rules, correcting movements by signaling the occurrence of motor errors. However, recent findings suggest that in some behaviors, CF activity can exhibit features that resemble the instructional signals necessary for reinforcement learning, namely reward prediction errors (rPEs). Despite these initial observations, many key properties of reward-related CF responses remain unclear, thus limiting our understanding of how they operate to guide cerebellar learning. Here, we have measured the postsynaptic responses of CFs onto cerebellar Purkinje cells using two-photon calcium imaging to test how they respond to learned stimuli that either do or do not predict reward. We find that CFs can develop generalized responses to similar cues of the same modality, regardless of whether they are reward predictive. However, this generalization depends on temporal context, and does not extend across sensory modalities. Further, learned CF responses are flexible, and can be rapidly updated according to new reward contingencies. Together these results suggest that CFs can generate learned, reward-predictive responses that flexibly adapt to the current environment in a context-sensitive manner.

Impact of the Minimization of Standard Deviation Before Zeroization of the Mean Bias on the Performance of IOL Power Formulas.

In cataract surgery, accurate intraocular lens (IOL) power calculations are crucial for optimal postoperative refractive outcomes. This study explores the impact of prioritizing the reduction of the standard deviation (SD) of prediction errors before mean prediction error (PE) adjustment on IOL calculation formula precision and accuracy. We conducted a retrospective analysis of 4885 eyes from 2611 patients, all implanted with the same IOL model, comparing four traditional IOL power calculation formulas: SRK/T, Holladay 1, Haigis, and Hoffer Q. We introduced new constants aiming to minimize the SD of PE (new_const) against traditionally optimized constants (classic_const), using a heteroscedastic statistical method for comparison. Validation of precision improvements used a secondary dataset of 262 eyes from 132 patients. We observed significant reductions in mean absolute error (MAE) across training and test sets for Hoffer Q, Holladay, and Haigis formulas, indicating accuracy enhancements. Optimized constants significantly reduced SDs for Haigis from 0.3255 to 0.3153 and for Hoffer Q from 0.3521 to 0.3387. These optimizations also increased the proportion of eyes achieving PE within ±0.25D. SRK/T showed improved SD from 0.3596 to 0.3585. However, Holladay 1 showed minimal change with no significant improvement. In the test dataset, significant reductions in SD were observed for Haigis and Hoffer Q. Prioritizing SD minimization before adjusting mean PE significantly improves the precision of selected IOL power formulas, enhancing postoperative refractive outcomes. The effectiveness varies among formulas, underscoring the need for formula-specific adjustments. The study presents a novel two-step approach for optimizing IOL power calculations.