Time Prediction Method Research Articles

Time Prediction in Ship Block Manufacturing Based on Transfer Learning

Accurate time prediction is critical to the success of ship block manufacturing. However, the emergence of new ship types with limited historical data poses challenges to existing prediction methods. In response, this paper proposes a novel framework for ship block manufacturing time prediction, integrating clustering and the transfer learning algorithm. Firstly, the concept of distributed centroids was innovatively adopted to achieve the clustering of categorical attribute features. Secondly, abundant historical data from other types of blocks (source domain) were incorporated into the neural network model to explore the effects of block features on manufacturing time, and the model was further transferred to blocks with limited data (target domain). Leveraging the similarities and differences between source and target domain blocks, actions involving freezing and fine-tuning parameters were adopted for the predictive model development. Despite a small sample size of only 80, our proposed block time prediction method achieves an impressive mean absolute percentage error (MAPE) of 8.62%. In contrast, the MAPE for the predictive model without a transfer learning algorithm is notably higher at 14.97%. Experimental validation demonstrates the superior performance of our approach compared to alternative methods in scenarios with small sample datasets. This research addresses a critical gap in ship block manufacturing time prediction.

An Adaptive Similar Scenario Matching Method for Predicting Aircraft Taxiing Time

Accurate prediction of taxiing time is important in ensuring efficient and safe operations on the airport surface. It helps improve ground operation efficiency, reduce fuel waste, and improve carbon emissions at the airport. In actual operations, taxiing time is influenced by various factors, including a large number of categorical features. However, few previous studies have focused on selecting such features. Additionally, traditional taxiing time prediction methods are often black-box models that only provide a single prediction result; they fail to provide effective practical references for controllers. Therefore, this paper analyses the features that affect taxiing time from different data types and forms a taxi feature set consisting of nine key features. We also propose a taxiing time prediction method based on adaptive scenario matching rules. This process classifies the scenarios into multiple typical historical scenario sets and adaptively matches the current target scenario to a typical scenario set based on quantified rules. Then, based on the matching results, a pre-trained model obtained from the corresponding scenario set is used to predict the taxiing time of an aircraft in the target scenario, aiming to mitigate the impact of data heterogeneity on prediction results. Experimental results show that compared to baseline methods, the mean absolute error and root mean square error of the proposed method decreased by 4.8% and 12.6%, respectively. This method significantly reduces the fluctuations in results caused by sample heterogeneity and enhances controllers’ acceptance of prediction results from the model. It can be used to further improve auxiliary decision making systems and enhance the precise control capabilities of airport surface operations.

RT-Transformer: retention time prediction for metabolite annotation to assist in metabolite identification.

Liquid chromatography retention times prediction can assist in metabolite identification, which is a critical task and challenge in nontargeted metabolomics. However, different chromatographic conditions may result in different retention times for the same metabolite. Current retention time prediction methods lack sufficient scalability to transfer from one specific chromatographic method to another. Therefore, we present RT-Transformer, a novel deep neural network model coupled with graph attention network and 1D-Transformer, which can predict retention times under any chromatographic methods. First, we obtain a pre-trained model by training RT-Transformer on the large small molecule retention time dataset containing 80038 molecules, and then transfer the resulting model to different chromatographic methods based on transfer learning. When tested on the small molecule retention time dataset, as other authors did, the average absolute error reached 27.30 after removing not retained molecules. Still, it reached 33.41 when no samples were removed. The pre-trained RT-Transformer was further transferred to 5 datasets corresponding to different chromatographic conditions and fine-tuned. According to the experimental results, RT-Transformer achieves competitive performance compared to state-of-the-art methods. In addition, RT-Transformer was applied to 41 external molecular retention time datasets. Extensive evaluations indicate that RT-Transformer has excellent scalability in predicting retention times for liquid chromatography and improves the accuracy of metabolite identification. The source code for the model is available at https://github.com/01dadada/RT-Transformer. The web server is available at https://huggingface.co/spaces/Xue-Jun/RT-Transformer.

BRT oil price combination forecasting based on the dispersion degree of triangular fuzzy numbers

Combination forecasting is an effective tool to improve the forecasting rate by combining single forecasting methods. The purpose of this paper is to apply a new combination forecasting model to predicting the BRT crude oil price based on the dispersion degree of two triangular fuzzy numbers with the circumcenter distance and radius of the circumcircle. First, a dispersion degree of two triangular fuzzy numbers is proposed to measure the triangular fuzzy numbers with the circumcenter distance and radius of the circumcircle, which can be used to predict the fluctuating trend and is suitable for crude oil futures price. Second, three single prediction methods (ARIMA, LSSVR and GRNN) are then presented to combine traditional statistical time set prediction with the latest machine learning time prediction methods which can strengthen the advantage and weaken the disadvantage. Finally, the practical example of crude oil price forecasting for London Brent crude futures is employed to illustrate the validity of the proposed forecasting method. The experimental results show that the proposed forecasting method produces much better forecasting performance than some existing triangular fuzzy models. The prediction error is reduced to 2.7 from 3–5 in oil price combination forecasting, in another comparison experiment the error is reduced to 0.0135 from 1. The proposed combination forecasting method, which fully capitalizes on the time sets forecasting model and intelligent algorithm, makes the triangular fuzzy prediction more accurate than before and has effective applicability.

Aircraft turnaround time dynamic prediction based on Time Transition Petri Net.

Accurate aircraft turnaround time prediction is an important way to coordinate the operation time of airport ground service and improve the efficiency of airport operation. In this paper, by analyzing the aircraft turnaround operation process, a description model based on Time Transition Petri Net is proposed. The model describes the flight turnaround operation process and the logical relationship of the operation. According to the model, a dynamic prediction method of turnaround time based on Bayesian theorem is designed. According to the actual landing time of the flight, the aircraft turnaround time is predicted. The specific method is to obtain the prior probability distribution and joint distribution law of each operation link according to the flight history data, and use Shapiro-Wilke to test the prior probability distribution of each link. Based on the analysis and comparison between the actual turnaround data of a large airport in China and the forecast data proposed in this paper, the root-mean-square error 3.75 minutes and the mean absolute error 3.40 minutes can be calculated. This paper contributes to the improvement of flight punctuality rate and airport clearance level.

Assessing the Performance of Remaining Time Prediction Methods for Business Processes

Assessing the Performance of Remaining Time Prediction Methods for Business Processes

Analysis of influencing factors of aircraft fuel tank flammability

PurposeIt is an indispensable part of airworthiness certification to evaluate the fuel tank flammability exposure time for transport aircraft. There are many factors and complex coupling relationships affecting the fuel tank flammability exposure time. The current work not only lacks a comprehensive analysis of these factors but also lacks the significance of each factor, the interaction relationship and the prediction method of flammability exposure time. The lack of research in these aspects seriously restricts the smooth development of the airworthiness forensics work of domestic large aircraft. This paper aims to clarify the internal relationship between user input parameters and predict the flammability exposure time of fuel tanks for transport aircraft.Design/methodology/approachBased on the requirements of airworthiness certification for large aircraft, an in-depth analysis of the Monte Carlo flammability evaluation source procedures specified in China Civil Aviation Regulation/FAR25 airworthiness regulations was made, the internal relationship between factors affecting the fuel tank flammability exposure time was clarified and the significant effects and interactions of input parameters in the Monte Carlo evaluation model were studied using the response surface method. And the BP artificial neural network training samples with high significance factors were used to establish the prediction model of flammability exposure time.FindingsThe input parameters in the Monte Carlo program directly or indirectly affect the fuel tank flammability exposure time by means of the influence on the flammability limit or fuel temperature. Among the factors affecting flammability exposure time, the cruising Mach number, balance temperature difference and maximum range are the most significant, and they are all positively correlated with flammability exposure time. Although there are interactions among all factors, the degree of influence on flammability exposure time is not the same. The interaction between maximum range and equilibrium temperature difference is more significant than other factors. The prediction model of flammability exposure time based on multifactor interaction and BP neural network has good accuracy and can be applied to the prediction of fuel tank flammability exposure time.Originality/valueThe flammability exposure time prediction model was established based on multifactor interaction and BP neural network. The limited test results were combined with intelligent algorithm to achieve rapid prediction, which saved the test cost and time.

An MBD-driven order remaining completion time prediction method based on SSA-BiLSTM in the IoT-enabled manufacturing workshop

The transformation of production mode leads to the need to strictly ensure the order in-time delivery. The global control ability of manufacturing workshops has become a necessary capability for enterprises. The real-time accurate Order Remaining Completion Time (ORCT) prediction allows managers to master the production schedule fluctuation, which provides criteria for workshop management. Due to the widespread deployment of Internet of Things (IoT) devices in the workshop, the difficulty of systematic processing and analysis of multi-dimensional heterogeneous data has been the main pain point of ORCT prediction. To tackle these problems, a Manufacturing Big Data (MBD)-driven ORCT prediction method based on Salp Swarm Algorithm (SSA) and Bidirectional Long Short-Term Memory (BiLSTM) is proposed. An attribute selection algorithm combined with max-relevance and min-redundancy and regularisation is used to mine key data from MBD. An SSA-BiLSTM model is proposed to achieve efficient and accurate ORCT prediction. The prediction model is supported by BiLSTM, and the hyperparameters are optimised by SSA. Finally, a case study about ORCT prediction in the IoT-enabled manufacturing workshop is presented. The result verifies that the proposed ORCT prediction method has obvious advantages over the other three traditional methods in accuracy and efficiency.

An improvement velocity inverse method for predicting the slope imminent failure time

The slope imminent failure time prediction method could be established with the slope surface deformation time curve before rupture. However, the existing time-to-failure prediction method does not unify the calculation time range, and the forecast results derived from the same model in different calculation time ranges could present significant differences. Taking Longjing rock fall in Guizhou and Dangchuan 4# loess flowslide in Gansu as examples, the calculation time ranges of imminent slope failure prediction were determined to be within the tangent angle of 80°–85° by analyzing the slope refined deformation data and using the velocity inverse method. The deformation curves have an obvious upward and sudden increase when the landslide is in the imminent stage, leading to an earlier landslide failure time. By analyzing the velocity inverse curve in the medium-term acceleration stage and the imminent sliding stage, a correction coefficient ranging from 0.30 to 0.55 was adopted to correct the landslide time prediction value. The results show that the improved prediction method for the slope imminent failure time has great accuracy and certain universality, which can mitigate the effects of slope failures in terms of both human lives and economic losses.

Prediction method of business process remaining time based on attention bidirectional recurrent neural network

<p align="justify">Most of the existing deep learning-based business process remaining time prediction methods use traditional long-short-term memory recurrent neural networks to build prediction models. Due to the limited modeling ability of traditional long-short-term memory recurrent neural networks for sequence data, and existing methods there is still much room for improvement in the prediction effect. Aiming at the shortcomings of existing methods, this paper proposes a business process remaining time prediction method based on attention bidirectional recurrent neural network. The method uses a bidirectional recurrent neural network to model the process instance data and introduces an attention mechanism to automatically learn the weights of different events in the process instance. In addition, in order to further improve the learning effect, an iterative learning strategy is designed based on the idea of transfer learning, which builds remaining time prediction models for process instances of different lengths, which improves the pertinence of the model. The experimental results show that the proposed method has obvious advantages compared with traditional methods.</p>

Computer Vision Aided mmWave Beam Alignment in V2X Communications

Visual information, captured for example by cameras, can effectively reflect the sizes and locations of the environmental scattering objects, and thereby can be used to infer communications parameters like propagation directions, receiver powers, as well as the blockage status. In this paper, we propose a novel beam alignment framework that leverages images taken by cameras installed at the mobile user. Specifically, we utilize 3D object detection techniques to extract the size and location information of the dynamic vehicles around the mobile user, and design a deep neural network (DNN) to infer the optimal beam pair for transceivers without any pilot signal overhead. Moreover, to avoid performing beam alignment too frequently or too slowly, a beam coherence time (BCT) prediction method is developed based on the vision information. This can effectively improve the transmission rate compared with the beam alignment approach with the fixed BCT. Simulation results show that the proposed vision based beam alignment methods outperform the existing LIDAR and vision based solutions, and demand for much lower hardware cost and communication overhead.

Performance-preserving event log sampling for predictive monitoring

Predictive process monitoring is a subfield of process mining that aims to estimate case or event features for running process instances. Such predictions are of significant interest to the process stakeholders. However, most of the state-of-the-art methods for predictive monitoring require the training of complex machine learning models, which is often inefficient. Moreover, most of these methods require a hyper-parameter optimization that requires several repetitions of the training process which is not feasible in many real-life applications. In this paper, we propose an instance selection procedure that allows sampling training process instances for prediction models. We show that our instance selection procedure allows for a significant increase of training speed for next activity and remaining time prediction methods while maintaining reliable levels of prediction accuracy.

A Method for Predicting Landslides Based on Micro-Deformation Monitoring Radar Data

Mine slope landslides seriously threaten the safety of people’s lives and property in mining areas. Landslide prediction is an effective way to reduce losses due to such disasters. In recent years, micro-deformation monitoring radar has been widely used in mine slope landslide monitoring. However, traditional landslide prediction methods are not able to make full use of the diversified monitoring data from these radars. This paper proposes a landslide time prediction method based on the time series monitoring data of micro-deformation monitoring radar. Specifically, deformation displacement, coherence and deformation volume, and the parametric degree of deformation (DOD) are calculated and combined with the use of the tangent angle method. Finally, the effectiveness of the method is verified by using measured data of a landslide in a mining area. The experimental results show that our proposed method can be used to identify the characteristics of an imminent sliding slope and landslide in advance, providing monitoring personnel with more reliable landslide prediction results.

Travel Time Prediction Method Based on Spatial-Feature-based Hierarchical Clustering and Deep Multi-input Gated Recurrent Unit

Accurate travel time prediction (TTP) is a significant aspect in the intelligent transportation system (ITS) . Travel times of certain road segments explicitly reflect the traffic conditions of those sections. Effective TTP of road segments is instrumental in route planning, traffic control, and traffic management. However, the accuracy of TTP is greatly affected by the intricate topological structure of traffic network and the dynamics of traffic flow over time. This paper develops a TTP method based on the spatial-feature-based hierarchical clustering (SFHC) and deep multi-input gated recurrent unit (DMGRU) . The proposed two-stage method is capable of capturing the spatial-temporal features of traffic network. Specifically, the SFHC divides the road segments into several clusters having similar traffic features, and then the clustered data is fed into the DMGRU for TTP. Our experiments conducted on the practical dataset demonstrate that the designed prediction method can achieve the mean absolute percentage error (MAPE) of 3.3109% and mean absolute error (MAE) of 2.5658, which outperform various combinations of baseline clustering algorithms and prediction models.

Risk-aware survival time prediction from whole slide pathological images

Deep-learning-based survival prediction can assist doctors by providing additional information for diagnosis by estimating the risk or time of death. The former focuses on ranking deaths among patients based on the Cox model, whereas the latter directly predicts the survival time of each patient. However, it is observed that survival time prediction for the patients, particularly with close observation times, possibly has incorrect orders, leading to low prediction accuracy. Therefore, in this paper, we present a whole slide image (WSI)-based survival time prediction method that takes advantage of both the risk as well as time prediction. Specifically, we propose to combine these two approaches by extracting the risk prediction features and using them as guides for the survival time prediction. Considering the high resolution of WSIs, we extract tumor patches from WSIs using a pre-trained tumor classifier and apply the graph convolutional network to aggregate information across these patches effectively. Extensive experiments demonstrate that the proposed method significantly improves the time prediction accuracy when compared with direct prediction of the survival times without guidance and outperforms existing methods.

World CO2 Emissions: Simple Analysis and its Relationship with Global Temperature Change

In the nature, booming CO2 emissions from the behaviors of human have adverse impact on the original Global Carbon Cycle. And this imbalance could cause the rise of global temperatures. This project collects the data of annual CO2 emissions as well as the global temperature change, trying to build their time-driving models independently with the help of regression functions and time prediction methods. By comparing between different models, we want to preliminary verify an assumption that there exists a limit of the ability of natural Global Carbon Cycle. If the amounts of CO2 in the atmosphere exceed this limit, the global temperature will increase. Also, whether the relationship between the increasing rate of global temperature and the CO2 emissions is linear or not is investigated. The conclusion shows that CO2 emissions and global temperature change have a strong and positive linear correlation, and if people produced less than around 20,000 Mt CO2 into the air, the global temperature could keep in dynamic equilibrium to some extent.

Spatial–temporal feature extraction based on convolutional neural networks for travel time prediction

AbstractIn recent years, some traffic information prediction methods have been proposed to provide the precise information on travel time, vehicle speed and traffic flow for highways. However, huge errors may be obtained by these methods for urban roads or alternative roads of highways. Therefore, this study proposes a travel time prediction method based on convolutional neural networks to extract important factors for the improvement of traffic information prediction. In practical experimental environments, the travel time records on No. 5 Highway and its alternative roads were collected and used to evaluate the proposed method. The results showed that the mean absolute percentage error of the proposed method was about 5.69%. Therefore, the proposed method based on deep‐learning techniques can improve the accuracy of travel time prediction.

Bayesian machine learning-based method for prediction of slope failure time

The data-driven phenomenological models based on deformation measurements have been widely utilized to predict the slope failure time (SFT). The observational and model uncertainties could lead the predicted SFT calculated from the phenomenological models to deviate from the actual SFT. Currently, very limited study has been conducted on how to evaluate the effect of such uncertainties on SFT prediction. In this paper, a comprehensive slope failure database was compiled. A Bayesian machine learning (BML)-based method was developed to learn the model and observational uncertainties involved in SFT prediction, through which the probabilistic distribution of the SFT can be obtained. This method was illustrated in detail with an example. Verification studies show that the BML-based method is superior to the traditional inverse velocity method (INVM) and the maximum likelihood method for predicting SFT. The proposed method in this study provides an effective tool for SFT prediction.

Transition-driven time prediction for business processes with cycles

Business process time prediction aims to predict the time of the running process instance, including the elapsed time and the predicted remaining time. Existing time prediction methods rarely take the cycles of business process into consideration. However, cycles of business process are one of the main factors affecting the accuracy of time prediction. To address this issue, a new transition-driven time prediction for business processes with cycles is proposed. First of all, on the one hand, a Petri net from the event log is mined to obtain the reachability graph, and then the transition division sequence is obtained from the reachability graph of a Petri net. On the other hand, the prefixes are generated by the event log, then, the prefix is feature-encoded and the corresponding business process time is calculated. Second, all prefixes are partitioned according to the activity of the last event of the prefix based on the transition division sequence. Finally, different autoencoders are applied to different transition divisions to reduce dimensionality, and transfer learning is performed by different deep neural networks. Furthermore, by extensive experimental evaluation using the publicly available synthetic event logs and real-life event logs, we show that the proposed method outperforms existing baseline methods.

Overall survival time prediction for glioblastoma using multimodal deep KNN

Glioblastoma (GBM) is a severe malignant brain tumor with bad prognosis, and overall survival (OS) time prediction is of great clinical value for customized treatment. Recently, many deep learning (DL) based methods have been proposed, and most of them build deep networks to directly map pre-operative images of patients to the OS time. However, such end-to-end prediction is sensitive to data inconsistency and noise. In this paper, inspired by the fact that clinicians usually evaluate patient prognosis according to previously encountered similar cases, we propose a novel multimodal deep KNN based OS time prediction method. Specifically, instead of the end-to-end prediction, for each input patient, our method first search its K nearest patients with known OS time in a learned metric space, and the final OS time of the input patient is jointly determined by the K nearest patients, which is robust to data inconsistency and noise. Moreover, to take advantage of multiple imaging modalities, a new inter-modality loss is introduced to encourage learning complementary features from different modalities. The in-house single-center dataset containing multimodal MR brain images of 78 GBM patients is used to evaluate our method. In addition, to demonstrate that our method is not limited to GBM, a public multi-center dataset (BRATS2019) containing 211 patients with low and high grade gliomas is also used in our experiment. As benefiting from the deep KNN and the inter-modality loss, our method outperforms all methods under evaluation in both datasets. To the best of our knowledge, this is the first work, which predicts the OS time of GBM patients in the strategy of KNN under the DL framework.