Time Prediction Research Articles

Reconciling spatiotemporal conjunction with digital twin for sequential travel time prediction and intelligent routing

Reconciling spatiotemporal conjunction with digital twin for sequential travel time prediction and intelligent routing

A digital hysteresis control method for three-level grid-tie inverter based on online prediction of sampling time without inductance

This article proposed a digital hysteresis control method for three-level grid-tie inverter based on online prediction of sampling time without inductance. The proposed method eliminated the effect on the control accuracy of the inductor changing with the current in the LCL filter of the grid-tie inverter, and reduced the equivalent sampling rate in digital hysteresis control by predicting and correcting the sample time. The simulations and experimental tests confirm the effectiveness of the proposed digital hysteresis control method.

Creep Effect on Time to Corrosion-Induced Cracking of Concrete Cover

AbstractThis paper presents an innovative method to include creep deformations in the prediction of time to corrosion-induced cover cracking. Using experimental results, creep and cracking criteria used in this method are verified. It is argued in the paper that the cover cracking problem under corrosion is close to a relaxation problem and the conventional creep formulations based on the effective elastic modulus cannot be adopted. It is found in the paper that accurate consideration of creep deformation would lead to about 30–40% longer time to cover cracking when compared to no consideration of creep deformations whilst for the currently practiced methods, the time can be up to 200% longer, which is unconservative in predicting time to cover cracking. Results in this paper open the debate on modelling of creep in the analysis of corrosion-affected structures and serve as an important step towards the accurate prediction of corrosion-induced concrete cracking.

Proposal and Validation of a New Index to Assess the Difficulty of Lower Third Molar Extraction

There is no current consensus on the parameters that determine the difficulty of mandibular third molar extraction in terms of the time required, which is essential to prevent complications and optimize the time of the intervention. This study aims to obtain, using the mathematical method of multiple linear regression, an equation that allows estimating the extraction time of a lower third molar according to its complexity, as well as to validate this equation in a sample of external wisdom teeth. Methods: A prospective cohort study on a sample of patients of the Master of Oral Surgery of the University of Seville in which multiple linear regression coefficients were calculated with a subsequent validation study of the results in the sample of patients operated in the Hospital Palmaplanas of Mallorca. Results: The regression line obtained after applying the statistical methodology to the cohort of patients from the University of Seville obtained significant dependent variables such as depth, roots, and odontosection. Once applied to the cohort of patients from the Palmaplanas Hospital in Mallorca, a regression coefficient was obtained between the data received and the estimated 0.770. Conclusions: The formula proposed in this article presents significant validity in the prediction of the surgical time of extraction of the lower third molars included.

Multi-Task Dynamic Spatio-Temporal Graph Attention Network: A Variable Taxi Time Prediction Model for Airport Surface Operation

Variable taxi time prediction is the core of the Airport Collaborative Decision Making (A-CDM) system. An accurate taxi time prediction contributes to enhancing airport operational efficiency, safety and predictability. The deep dynamic spatio-temporal correlation inherent in airport traffic data is critical for taxi time prediction. However, existing machine learning (deep learning) methods have been unable to thoroughly exploit these correlations. To address this issue, we propose a deep learning-based model called the multi-task dynamic spatio-temporal graph attention network (MT-DSTGAN). Our model also predicts future entire airport traffic flow and taxiing segment traffic flow as auxiliary tasks, with the goal of enhancing the accuracy of aircrafts’ taxi time prediction. The proposed MT-DSTGAN model is implemented and assessed through a case study of Beijing Capital International Airport with a real-world dataset. The advantage of the proposed model, which shows better performance in various evaluation metrics, is demonstrated in a comparative study with other baseline works. In summary, the proposed MT-DSTGAN exhibits promising capabilities in perceiving the dynamic changes in the taxiing process of aircraft and demonstrates the ability to capture complex spatio-temporal correlations in airport traffic data.

Predicting Bus Travel Time in Cheonan City Through Deep Learning Utilizing Digital Tachograph Data

Urban transportation systems are increasingly burdened by traffic congestion, a consequence of population growth and heightened reliance on private vehicles. This congestion not only disrupts travel efficiency but also undermines productivity and urban resident’s overall well-being. A critical step in addressing this challenge is the accurate prediction of bus travel times, which is essential for mitigating congestion and improving the experience of public transport users. To tackle this issue, this study introduces the Hybrid Temporal Forecasting Network (HTF-NET) model, a framework that integrates machine learning techniques. The model combines an attention mechanism with Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) layers, enhancing its predictive capabilities. Further refinement is achieved through a Support Vector Regressor (SVR), enabling the generation of precise bus travel time predictions. To evaluate the performance of the HTF-NET model, comparative analyses are conducted with six deep learning models using real-world digital tachograph (DTG) data obtained from intracity buses in Cheonan City, South Korea. These models includes various architectures, including different configurations of LSTM and GRU, such as bidirectional and stacked architectures. The primary focus of the study is on predicting travel times from the Namchang Village bus stop to the Dongnam-gu Public Health Center, a crucial route in the urban transport network. Various experimental scenarios are explored, incorporating overall test data, and weekday and weekend data, with and without weather information, and considering different route lengths. Comparative evaluations against a baseline ARIMA model underscore the performance of the HTF-NET model. Particularly noteworthy is the significant improvement in prediction accuracy achieved through the incorporation of weather data. Evaluation metrics, including root mean squared error (RMSE), mean absolute error (MAE), and mean squared error (MSE), consistently highlight the superiority of the HTF-NET model, outperforming the baseline ARIMA model by a margin of 63.27% in terms of the RMSE. These findings provide valuable insights for transit agencies and policymakers, facilitating informed decisions regarding the management and optimization of public transportation systems.

Enhancing vessel arrival time prediction: A fusion-based deep learning approach

The logistic community of shippers has struggled to predict the precise arrival time of the seagoing vessels with reliable certainty. While deep-learning approaches are promising, the existing methods fail to provide desirable results due to a shallow prediction architecture. This research work proposes a method to predict vessel arrival time that could eventually be incorporated into an intelligent decision support system that we call Vessel Arrival Time Prediction (VATP). VATP presents a hybrid architecture of Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), Attention mechanism, Dropout, and Dense layers to take advantage of the coarse-grained local features produced by CNN, the longitudinal nature of AIS (long-time dependencies) via LSTM and paying attention to the influence feature on the arrival time. While many prior approaches have relied solely on AIS data, and some incorporated a combination of AIS and vessel information, our method also integrates diverse data sources, including Automatic Identification System (AIS), Augmented information (Ain), and Maritime Weather Data (MWD). Furthermore, only a few methods have considered weather information, often using minimal weather-related features. In contrast, our approach involves a comprehensive range of weather-related features, and besides these data sources, we extracted specially crafted features.To verify the effectiveness of VATP, we conducted our experiment on large-scale datasets. The VATP model obtained a Root Mean Square Error (RMSE) of 10.63 and a Mean Absolute Percentage Error (MAPE) of 35.11 %. Our results demonstrate that VATP achieves significant performance. Furthermore, these positive results demonstrate that i) the accuracy of the VATP approach can be improved using the AIS, MWD, and Ain information; ii) learning from a unified feature set can result in a significant performance improvement compared to learning from a subset of the features; iii) we also obtained a superior performance in comparison with other well-known methods in the literature and various state-of-the-art baseline methods. Finally, our results illustrate the consistent performance of the VATP across different datasets.

Soft sensor development for mixed oil interface tracking in multi-product pipelines based on knowledge-informed semi-supervised Variational Bayesian Gaussian mixture regression

Sequential transportation of petroleum products in multi-product pipelines often lead to occurrence of mixed oil. The prediction of the arrival time of the mixed oil interface constitutes crucial data for the scheduling of treatment actions. However, existing soft sensors, like Gaussian mixture regression (GMR), may face challenges due to limited size of labeled data and numerical issues, leading to performance degradation or even training failure. To tackle these issues, we propose a Knowledge-informed Semi-supervised Variational Bayesian Gaussian mixture model (KI-SSVBGMR). It employs a semi-supervised fully Bayesian structure designed to address the constraints arising from the potential matrix singularity issues and shortage of labeled samples. Subsequently, we determine the crucial regression variable and establish its prior distribution based on industrial knowledge to improve model generalization. Finally, a learning procedure grounded in the Variational Inference algorithm is developed to train the KI-SSVBGMR. Through case studies, including numerical examples and real industrial datasets, our method demonstrates the effectiveness and reliability of the proposed soft sensor development method. This research can aid operators in improving mixed oil section management and provides valuable insights for integrating machine learning with industrial knowledge.

A Hydrodynamic‐Based Physical Unified Modeling for Simulating Shallow Landslide Local Failures, Mass Release and Debris Flow Run‐Out Extent Behavior

AbstractAccurate prediction of shallow landslide occurrence and the subsequent motion range after transformation into debris flows is crucial for reducing disaster‐induced losses. The use of Cellular Automata‐based (CA) hydrodynamic models has seen increasing application in predicting landslides, debris flows, and other related hazards. However, previous CA‐based models have primarily focused on the motion and evolution process of debris flows, lacking detailed description about the dynamic instability associated with shallow landslides. In this study, we propose a comprehensive CA‐based model that is based on existing theories and improved models for simulating hydrological processes, sliding surface identification algorithms, threshold‐based mechanical interactions, material entrainment, and deposition. The model was applied to the Yindongzi (YDZ) landslides in Sichuan, China. The accuracy of the model was validated through comparisons with field investigation results and calculations based on shallow water equations. This model enables efficient and rapid prediction of shallow landslide occurrence time, volume, spatial distribution, and runout distance. Evaluation of the model’s predictive performance reveals an error range of −23.12% to +44.26% for YDZ landslides. Moreover, the influence of different shallow landslide failure patterns on the deposition and erosion of debris flows was analyzed. The results indicate that the failure patterns of shallow landslides significantly affect the deposition and entrainment capacity of debris flows. This study provides a novel approach for predicting the occurrence of shallow landslides and the subsequent motion, entrainment, and deposition after transformation into debris flows.

Analysis of the sodium pump subunit ATP1A3 in glioma patients: Potential value in prognostic prediction and immunotherapy

The ATP1A3 gene is associated with the development and progression of neurological diseases. However, the pathological function and therapeutic value of ATP1A3 in glioblastoma (GBM) remains unknown. In this study, we tried to explore the correlation between the ATP1A3 gene expression and immune features in GBM samples. We found that ATP1A3 gene expression levels showed significant negative correlation with immune checkpoints such as PD-L1, CTLA-4 and IDO1. Next, ATP1A3 gene expression levels showed significant negative correlation with the anti-cancer immune cell process, the immune score and stromal score. By grouping ATP1A3 expression levels, we found that that immunomodulator-related genes and tumor-associated immune cell effector gene expression levels were associated with lower ATP1A3 expression. In addition, immunotherapy prediction pathway activity and a majority of the anti-cancer immune cell process activity levels were also showed to be correlated with lower ATP1A3 gene expression. Further, nine prognostic factors were identified by prognostic analysis, and a GBM prognostic model (risk score) was established. We applied the model to the TCGA GBM training set sample and the GSE4412 validation set sample and found that patients in the high risk score subgroup had significantly shorter survival time, demonstrating the prognostic value and prognostic efficacy of the risk score. Furthermore, ATP1A3 overexpression has also been found to sensitize cancer cells to anti-PD-1 therapy. In conclusion, we showed that ATP1A3 is a highly promising treatment target in GBM and the risk score is an independent prognostic factor for cancer and can be used to help guide the prediction of survival time in patients with GBM.

Enhancing LC×LC separations through multi-task Bayesian optimization

Method development in comprehensive two-dimensional liquid chromatography (LC×LC) is a challenging process. The interdependencies between the two dimensions and the possibility of incorporating complex gradient profiles, such as multi-segmented gradients or shifting gradients, make trial-and-error method development time-consuming and highly dependent on user experience. Retention modeling and Bayesian optimization (BO) have been proposed as solutions to mitigate these issues. However, both approaches have their strengths and weaknesses. On the one hand, retention modeling, which approximates true retention behavior, depends on effective peak tracking and accurate retention time and width predictions, which are increasingly challenging for complex samples and advanced gradient assemblies. On the other hand, Bayesian optimization may require many experiments when dealing with many adjustable parameters, as in LC×LC. Therefore, in this work, we investigate the use of multi-task Bayesian optimization (MTBO), a method that can combine information from both retention modeling and experimental measurements. The algorithm was first tested and compared with BO using a synthetic retention modeling test case, where it was shown that MTBO finds better optima with fewer method-development iterations than conventional BO. Next, the algorithm was tested on the optimization of a method for a pesticide sample and we found that the algorithm was able to improve upon the initial scanning experiments. Multi-task Bayesian optimization is a promising technique in situations where modeling retention is challenging, and the high number of adjustable parameters and/or limited optimization budget makes traditional Bayesian optimization impractical.

Prediction of clog time of amorphous silica in the pipes of the wells from Los Humeros geothermal field – A new geochemical model along with a computational algorithm

The primary objective of this article is to introduce a physicochemical model along with a computational algorithm that is valuable for quantifying the occurrence of silica scaling and fouling within geothermal production wells. This model utilizes two-phase flow parameters, temperature and pressure profiles, as well as brine composition to forecast the timing of production pipe constriction caused by amorphous silica deposition over time. The model is applicable to systems with temperatures ranging from 270°C to 305°C, vapor pressures ranging from 55 to 93 bars, and enthalpies ranging from 1189 kJ/kg to 1400 kJ/kg. The predictive model was calibrated using data gathered from six distinct wells within the Los Humeros geothermal field in Mexico, and subsequently, it was applied to forecast outcomes in two additional wells. When the conditions of temperature, pressure, and enthalpy remain relatively constant throughout the production process, the model developed in this study accurately predicts the times at which a certain percentage of pipe sealing occurs in wells with high volumetric fractions of liquid (εl>0.5) and temperatures between 270°C and 305°C. The prediction error is less than 3%.

Mixing Time Prediction in a Ladle Furnace

Mixing Time Prediction in a Ladle Furnace

Using data-driven techniques to predict outpatient ultrasound examination time for the multi-clinic outpatient appointment scheduling problem

Appointment scheduling for hospital patients is becoming increasingly important because it can reduce patient’s waiting time and enhance hospitals’ medical quality. In the case of ultrasound examinations, multiple radiological technologists use multiple rooms to conduct examinations, which involves the sequencing of examination work, time uncertainty, and operational characteristics. To enable hospital managers to effectively evaluate radiological technologists’ effort when carrying out ultrasound examinations, this study uses classification methods in data exploration, including decision tree (DT), logistic regression (LR), and artificial neural network (ANN), to establish a time prediction model for outpatient ultrasound examination. This study found that the DT model (i.e. C4.5) had the highest classification accuracy. After reviewing and removing rules generated from the model with an accuracy below 70%, the overall accuracy of the model was 76.31%. The classification results of the model are a reference for outpatient ultrasound appointment scheduling. The results of the study can effectively predict the examination time needed for ultrasound outpatients requiring different examination positions, thereby fairly allocating the patients to each room for the examination and reducing patient waiting time and radiological technologists’ idle time. Therefore, hospital managers can improve the hospital’s overall medical quality.

Electrothermal Model Based Remaining Charging Time Prediction of Lithium-Ion Batteries against Wide Temperature Range

Battery remaining charging time (RCT) prediction can facilitate charging management and alleviate mileage anxiety for electric vehicles (EVs). Also, it is of great significance to improve EV users' experience. However, the RCT for a lithium-ion battery pack in EVs changes with temperature and other battery parameters. This study proposes an electrothermal model-based method to accurately predict battery RCT. Firstly, a characteristic battery cell is adopted to represent the battery pack, thus an equivalent circuit model (ECM) of the characteristic battery cell is established to describe the electrical behaviors of a battery pack. Secondly, an equivalent thermal model (ETM) of the battery pack is developed by considering the influence of ambient temperature, thermal management, and battery connectors in the battery pack to calculate the temperature which is then fed back to the ECM to realize electrothermal coupling. Finally, the RCT prediction method is proposed based on the electrothermal model and validated in the wide temperature range from − 20 ℃ to 45 ℃. The experimental results show that the prediction error of the RCT in the whole temperature range is less than 1.5%.

Implementation of Real-Time Bus Tracking and Passenger Information System for MSRTC Mr. Vikrant Talole, Mr. Prasad Sonavane, Miss. Snehal Saykar

The "Real-Time Bus Tracking and Passenger Information System for Maharashtra State Road Transport Corporation (MSRTC)" is a cutting-edge technological solution designed to revolutionize the public transportation experience. In a world where efficiency, accuracy, and real-time information are paramount, this system stands as a beacon of innovation. The system offers real-time tracking capabilities, allowing passengers to monitor the exact location of MSRTC buses in real-time through intuitive mobile applications and web interfaces. Leveraging GPS technology, this feature not only ensures accurate tracking but also enables precise predictions of bus arrival times at designated stops. Passengers gain access to comprehensive route information, including stops, schedules, and landmarks, enhancing their ability to plan journeys effectively. The Real Time Bus Tracking and Passenger Information System for MSRTC stands as a testament to the power of innovation, ushering in a new era of smart public transportation.

Random forests for survival data: which methods work best and under what conditions?

Few systematic comparisons of methods for constructing survival trees and forests exist in the literature. Importantly, when the goal is to predict a survival time or estimate a survival function, the optimal choice of method is unclear. We use an extensive simulation study to systematically investigate various factors that influence survival forest performance - forest construction method, censoring, sample size, distribution of the response, structure of the linear predictor, and presence of correlated or noisy covariates. In particular, we study 11 methods that have recently been proposed in the literature and identify 6 top performers. We find that all the factors that we investigate have significant impact on the methods' relative accuracy of point predictions of survival times and survival function estimates. We use our results to make recommendations for which methods to use in a given context and offer explanations for the observed differences in relative performance.

Iterative kernel regression with preconditioning

Kernel methods are popular in nonlinear and nonparametric regression due to their solid mathematical foundations and optimal statistical properties. However, scalability remains the primary bottleneck in applying kernel methods to large-scale data regression analysis. This paper aims to improve the scalability of kernel methods. We combine Nyström subsampling and the preconditioned conjugate gradient method to solve regularized kernel regression. Our theoretical analysis indicates that achieving optimal convergence rates requires only [Formula: see text] memory and [Formula: see text] time (up to logarithmic factors). Numerical experiments show that our algorithm outperforms existing methods in time efficiency and prediction accuracy on large-scale datasets. Notably, compared to the FALKON algorithm [A. Rudi, L. Carratino and L. Rosasco, Falkon: An optimal large scale kernel method, in Advances in Neural Information Processing Systems (Curran Associates, 2017), pp. 3891–3901], which is known as the optimal large-scale kernel method, our method is more flexible (applicable to non-positive definite kernel functions) and has a lower algorithmic complexity. Additionally, our established theoretical analysis further relaxes the restrictive conditions on hyperparameters previously imposed in convergence analyses.

Facile one-step nanoporous alumina for modifying the surface optical properties of ITO glass

Structure color is a useful technique with good brightness, variuos color, and friendly environmental properties, compared with the dyes and pigments colors. However, the structure colors are based on the micro- or nano structures, which is still a challenge for fabricating the desired colors. Anodic aluminum oxide (AAO) is a common nanomaterial for fabricating the structure colors because of the properties of hardness, stability, and the self-assembly. However, current techniques mostly manufactured the structure color on the aluminum foils or the alloy, which limited these techniques from the glass-based applications. Additionally, current technologies usually require a time-consuming fabrication process lasting several tens of hours. In this study, a facile method is proposed for producing structure colors on transparent ITO glass through AAO coating with a short fabrication time. The vibrant structure colors result from constructive interference of visible light due to the nanoporous AAO film on the ITO glass substrate. Furthermore, a correlation between the anodization time of AAO and color is established, enabling the prediction of anodization time to achieve the desired color without resorting to a trial-and-error approach. A spectrum of colors within the visible light range, spanning wavelengths from 420 to 740 nm, is successfully demonstrated on the ITO glass using this uncomplicated one-step anodization process.

Kinetics of initial diffusion solidification during continuous heating in term of IN718 superalloy / 316LN steel TLP bonding system

In this work, the effect of heating rate on the solidification kinetics of the dissimilar transient liquid phase (TLP) bonding joint of IN718 superalloy / 316LN steel was investigated. It was determined that the initial diffusion solidification (IDS) during continuous heating, accompanied by the melting of interlayer, plays an important role on the formation of TLP bonding joint. The lower heating rate results in the more sufficient IDS and thus the shorter time needed for isothermal solidification. This overturns the conventional view that the solidification behavior in TLP bonding joints mainly occurs at the stage of isothermal holding. Additionally, the IDS process is modeled using diffusion-based concepts under varying heating rates. The proposed model is more applicable for the prediction of solidification time in TLP bonding joint than the classic models only on the consideration of isothermal solidification.