Search results

Metropolitan areas suffer from frequent road traffic congestion not only during peak hours but also during off-peak periods. Different machine learning methods have been used in travel time prediction, however, such machine learning methods practically face the problem of overfitting. Tree-based ensembles have been applied in various prediction fields, and such approaches usually produce high prediction accuracy by aggregating and averaging individual decision trees. The inherent advantages of these approaches not only get better prediction results but also have a good bias-variance trade-off which can help to avoid overfitting. However, the reality is that the application of tree-based integration algorithms in traffic prediction is still limited. This study aims to improve the accuracy and interpretability of the models by using random forest (RF) to analyze and model the travel time on freeways.

As the traffic conditions often greatly change, the prediction results are often unsatisfactory. To improve the accuracy of short-term travel time prediction in the freeway network, a practically feasible and computationally efficient RF prediction method for real-world freeways by using probe traffic data was generated. In addition, the variables’ relative importance was ranked, which provides an investigation platform to gain a better understanding of how different contributing factors might affect travel time on freeways.

The parameters of the RF model were estimated by using the training sample set. After the parameter tuning process was completed, the proposed RF model was developed. The features’ relative importance showed that the variables (travel time 15 min before) and time of day (TOD) contribute the most to the predicted travel time result. The model performance was also evaluated and compared against the extreme gradient boosting method and the results indicated that the RF always produces more accurate travel time predictions.

This research developed an RF method to predict the freeway travel time by using the probe vehicle-based traffic data and weather data. Detailed information about the input variables and data pre-processing were presented. To measure the effectiveness of proposed travel time prediction algorithms, the mean absolute percentage errors were computed for different observation segments combined with different prediction horizons ranging from 15 to 60 min.

Many transport and logistics companies nowadays use raw vehicle GPS data for travel time prediction. However, they face difficult challenges in terms of the costs of information storage, as well as the quality of the prediction. This paper aims to systematically investigate various meta-data (features) that require significantly less storage space but provide sufficient information for high-quality travel time predictions.

The paper systematically studied the combinatorial effects of features and different model fitting strategies with two popular decision tree ensemble methods for travel time prediction, namely, random forests and gradient boosting regression trees. First, the investigation was conducted using pseudo travel time data that were generated using a pseudo travel time sampling algorithm, which allows generating travel time data using different noise processes so that the prediction performance under different travel conditions and noise characteristics can be studied systematically. The results and findings were then further compared and evaluated through a real-life case.

The paper provides empirical insights and guidelines about how raw GPS data can be reduced into a small-sized feature vector for the purposes of vehicle travel time prediction. It suggests that, add travel time observations from the previous departure time intervals are beneficial to the prediction, particularly when there is no other types of real-time information (e.g. traffic flow, speed) are available. It was also found that modular model fitting does not improve the quality of the prediction in all experimental settings used in this paper.

The findings are primarily based on empirical studies on limited real-life data instances, and the results may lack generalisabilities. Therefore, the researchers are encouraged to test them further in more real-life data instances.

The paper includes implications and guidelines for the development of efficient GPS data storage and high-quality travel time prediction under different types of travel conditions.

This paper systematically studies the combinatorial feature effects for tree-ensemble-based travel time prediction approaches.

Based on virtual maintenance, this paper aims to propose a time prediction method of assembly and disassembly (A&D) actions of product maintenance process to enhance existing methods’ prediction accuracy, applicability and efficiency.

First, a framework of A&D time prediction model is constructed, which describes the time prediction process in detail. Then, basic maintenance motions which can comprise a whole A&D process are classified into five categories: body movement, working posture change, upper limb movement, operation and grasp/placement. A standard posture library is developed based on the classification. Next, according to motion characteristics, different time prediction methods for each motion category are proposed based on virtual maintenance simulation, modular arrangement of predetermined time standard theory and the statistics acquired from motion experiment. Finally, time correction based on the quantitative evaluation method of motion time influence factors is studied so that A&D time could be predicted with more accuracy.

Case study of time prediction of products’ various A&D processes is conducted by implementing the proposed method. The prediction process of diesel cooling fan disassemble time is presented in detail. Through comparison, the advantages and effectiveness of the method are demonstrated.

This paper proposes a more accurate, efficient and applicable product A&D time prediction method. It can help designers predict A&D time of a product maintenance accurately in early design phases without a physical prototype. It can also provide basis for the verification of maintainability, the balance of the design of product structure and system layout.

Process mining provides a new means to improve processes in a variety of application domains. The purpose of this paper is to abstract a process model and then use the discovered models from process mining to make useful optimization via predictions.

The paper divides the process model into a combination of “pair-adjacent activities” and “pair-adjacent persons” in the event logs. First, two new handover process models based on adjacency matrix are proposed. Second, by adding the stage, frequency, and time for every activity or person into the matrix, another two new handover prediction process models based on stage adjacency matrix are further proposed. Third, compute the conditional probability from every stage to next stage through the frequency. Finally, use real data to analyze and demonstrate the practicality and effectiveness of the proposed handover optimization process.

The process model can be extended with information to predict what will actually happen, how possible to reach the next activity, who will do this activity, and the corresponding probability if there are several people executing the same activity, etc.

The contribution of this paper is to predict what will actually happen, how possible it is to reach the following activities or persons in the next stage, how soon to reach the following activities or persons by calculating all the possible interval time via different traces, who will do this activity, and the corresponding probability if there are several people executing the same activity, etc.

The goal is to assess performance prediction systems (PPS) that are used to assist at-risk learners.

The authors propose time-dependent metrics including earliness and stability. The authors investigate the relationships between the various temporal metrics and the precision metrics in order to identify the key earliness points in the prediction process. Authors propose an algorithm for computing earliness. Furthermore, the authors propose using an earliness-stability score (ESS) to investigate the relationship between the earliness of a classifier and its stability. The ESS is used to examine the trade-off between only time-dependent metrics. The aim is to compare its use to the earliness-accuracy score (EAS).

Stability and accuracy are proportional when the system's accuracy increases or decreases over time. However, when the accuracy stagnates or varies slightly, the system's stability is decreasing rather than stagnating. As a result, the use of ESS and EAS is complementary and allows for a better definition of the point of earliness in time by studying the relation-ship between earliness and accuracy on the one hand and earliness and stability on the other.

When evaluating the performance of PPS, the temporal dimension is an important factor that is overlooked by traditional measures current metrics are not well suited to assessing PPS’s ability to predict correctly at the earliest, as well as monitoring predictions stability and evolution over time. Thus, in this work, the authors propose time-dependent metrics, including earliness, stability and the trade-offs, with objective to assess PPS over time.

The purpose of this paper is to present a new quantum‐inspired evolutionary hybrid intelligent (QIEHI) approach, in order to overcome the random walk dilemma for stock market prediction.

The proposed QIEHI method is inspired by the Takens' theorem and performs a quantum‐inspired evolutionary search for the minimum necessary dimension (time lags) embedded in the problem for determining the characteristic phase space that generates the financial time series phenomenon. The approach presented in this paper consists of a quantum‐inspired intelligent model composed of an artificial neural network (ANN) with a modified quantum‐inspired evolutionary algorithm (MQIEA), which is able to evolve the complete ANN architecture and parameters (pruning process), the ANN training algorithm (used to further improve the ANN parameters supplied by the MQIEA), and the most suitable time lags, to better describe the time series phenomenon.

This paper finds that, initially, the proposed QIEHI method chooses the better prediction model, then it performs a behavioral statistical test to adjust time phase distortions that appear in financial time series. Also, an experimental analysis is conducted with the proposed approach using six real‐word stock market times series, and the obtained results are discussed and compared, according to a group of relevant performance metrics, to results found with multilayer perceptron networks and the previously introduced time‐delay added evolutionary forecasting method.

The paper usefully demonstrates how the proposed QIEHI method chooses the best prediction model for the times series representation and performs a behavioral statistical test to adjust time phase distortions that frequently appear in financial time series.

The purpose of this paper is to propose a data prediction framework for scenarios which require forecasting demand for large-scale data sources, e.g., sensor networks, securities exchange, electric power secondary system, etc. Concretely, the proposed framework should handle several difficult requirements including the management of gigantic data sources, the need for a fast self-adaptive algorithm, the relatively accurate prediction of multiple time series, and the real-time demand.

First, the autoregressive integrated moving average-based prediction algorithm is introduced. Second, the processing framework is designed, which includes a time-series data storage model based on the HBase, and a real-time distributed prediction platform based on Storm. Then, the work principle of this platform is described. Finally, a proof-of-concept testbed is illustrated to verify the proposed framework.

Several tests based on Power Grid monitoring data are provided for the proposed framework. The experimental results indicate that prediction data are basically consistent with actual data, processing efficiency is relatively high, and resources consumption is reasonable.

This paper provides a distributed real-time data prediction framework for large-scale time-series data, which can exactly achieve the requirement of the effective management, prediction efficiency, accuracy, and high concurrency for massive data sources.

It is possible to see effective use of Artificial Intelligence-based systems in many fields because it easily outperforms traditional solutions or provides solutions for the problems not previously solved. Prediction applications are a widely used mechanism in research because they allow for forecasting of future states. Logical inference mechanisms in the field of Artificial Intelligence allow for faster and more accurate and powerful computation. Machine Learning, which is a sub-field of Artificial Intelligence, has been used as a tool for creating effective solutions for prediction problems.

In this chapter the authors will focus on employing Machine Learning techniques for predicting data for future states of economic using techniques which include Artificial Neural Networks, Adaptive Neuro-Fuzzy Inference System, Dynamic Boltzmann Machine, Support Vector Machine, Hidden Markov Model, Bayesian Learning on Gaussian process model, Autoregressive Integrated Moving Average, Autoregressive Model (Poggi, Muselli, Notton, Cristofari, & Louche, 2003), and K-Nearest Neighbor Algorithm. Findings revealed positive results in terms of predicting economic data.

Higher energy conversion efficiency of internal combustion engine can be achieved with optimal control of unsteady in-cylinder flow fields inside a direct-injection (DI) engine. However, it remains a daunting task to predict the nonlinear and transient in-cylinder flow motion because they are highly complex which change both in space and time. Recently, machine learning methods have demonstrated great promises to infer relatively simple temporal flow field development. This paper aims to feature a physics-guided machine learning approach to realize high accuracy and generalization prediction for complex swirl-induced flow field motions.

To achieve high-fidelity time-series prediction of unsteady engine flow fields, this work features an automated machine learning framework with the following objectives: (1) The spatiotemporal physical constraint of the flow field structure is transferred to machine learning structure. (2) The ML inputs and targets are efficiently designed that ensure high model convergence with limited sets of experiments. (3) The prediction results are optimized by ensemble learning mechanism within the automated machine learning framework.

The proposed data-driven framework is proven effective in different time periods and different extent of unsteadiness of the flow dynamics, and the predicted flow fields are highly similar to the target field under various complex flow patterns. Among the described framework designs, the utilization of spatial flow field structure is the featured improvement to the time-series flow field prediction process.

The proposed flow field prediction framework could be generalized to different crank angle periods, cycles and swirl ratio conditions, which could greatly promote real-time flow control and reduce experiments on in-cylinder flow field measurement and diagnostics.

With the continuous growth of online education, the quality issue of online educational videos has become increasingly prominent, causing students in online learning to face the dilemma of knowledge confusion. The existing mechanisms for controlling the quality of online educational videos suffer from subjectivity and low timeliness. Monitoring the quality of online educational videos involves analyzing metadata features and log data, which is an important aspect. With the development of artificial intelligence technology, deep learning techniques with strong predictive capabilities can provide new methods for predicting the quality of online educational videos, effectively overcoming the shortcomings of existing methods. The purpose of this study is to find a deep neural network that can model the dynamic and static features of the video itself, as well as the relationships between videos, to achieve dynamic monitoring of the quality of online educational videos.

The quality of a video cannot be directly measured. According to previous research, the authors use engagement to represent the level of video quality. Engagement is the normalized participation time, which represents the degree to which learners tend to participate in the video. Based on existing public data sets, this study designs an online educational video engagement prediction model based on dynamic graph neural networks (DGNNs). The model is trained based on the video’s static features and dynamic features generated after its release by constructing dynamic graph data. The model includes a spatiotemporal feature extraction layer composed of DGNNs, which can effectively extract the time and space features contained in the video's dynamic graph data. The trained model is used to predict the engagement level of learners with the video on day T after its release, thereby achieving dynamic monitoring of video quality.

Models with spatiotemporal feature extraction layers consisting of four types of DGNNs can accurately predict the engagement level of online educational videos. Of these, the model using the temporal graph convolutional neural network has the smallest prediction error. In dynamic graph construction, using cosine similarity and Euclidean distance functions with reasonable threshold settings can construct a structurally appropriate dynamic graph. In the training of this model, the amount of historical time series data used will affect the model’s predictive performance. The more historical time series data used, the smaller the prediction error of the trained model.

A limitation of this study is that not all video data in the data set was used to construct the dynamic graph due to memory constraints. In addition, the DGNNs used in the spatiotemporal feature extraction layer are relatively conventional.

In this study, the authors propose an online educational video engagement prediction model based on DGNNs, which can achieve the dynamic monitoring of video quality. The model can be applied as part of a video quality monitoring mechanism for various online educational resource platforms.