Predicting duration of traffic accidents based on cost-sensitive Bayesian network and weighted K-nearest neighbor

Kuang, Li; Yan, Han; Zhu, Yujia; Tu, Shenmei; Fan, Xiaoliang

doi:10.1080/15472450.2018.1536978

Cited by 75 publications

(25 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another advantage is its non-parametric nature, making it well suited to analyze nonlinear and complex relationships (Nemes et al, 2006;Abedi et al, 2018). Researchers have used the kNN because of its capacity to predict a large set of attributes simultaneously (e.g., Mittal et al, 2018;Kuang et al, 2019;Lee et al, 2019). Therefore, it is a cost-and time-effective modelling approach to use in spatially extensive regions (Beaudoin et al, 2014).…”

Section: A Ranking Of the Modelsmentioning

confidence: 99%

Predicting uncertainty of machine learning models for modelling nitrate pollution of groundwater using quantile regression and UNEEC methods

Rahmati

Choubin

Fathabadi

et al. 2019

Science of The Total Environment

181

View full text Add to dashboard Cite

Although estimating the uncertainty of models used for modelling nitrate contamination of groundwater is essential in groundwater management, it has been generally ignored. This issue motivates this research to explore the predictive uncertainty of machine-learning (ML) models in this field of study using two different residuals uncertainty methods: quantile regression (QR) and uncertainty estimation based on local errors and clustering (UNEEC). Prediction-interval coverage

show abstract

Section: A Ranking Of the Modelsmentioning

confidence: 99%

Predicting uncertainty of machine learning models for modelling nitrate pollution of groundwater using quantile regression and UNEEC methods

Rahmati

Choubin

Fathabadi

et al. 2019

Science of The Total Environment

181

View full text Add to dashboard Cite

show abstract

“…Therefore, the execution time is fixed and the response time can be directly reflected by the completion time (Figure 8). Because the QoS parameter fault tolerance algorithm in this paper takes into account the completion time of each task and the cumulative attribute of cost, the parameter fault tolerance algorithm at light load is not superior to the timefirst algorithm in time; and as the number of tasks increases, the system throughput the amount is reduced, and the advantage of the scheduling fault-tolerant algorithm is gradually reflected when the complexity is increased [20]. It saves a lot more than the task completion time of the time optimization algorithm.…”

Section: B Results Analysismentioning

confidence: 99%

Grid Quality of Service Trustworthiness Evaluation Based on Bayesian Network

Huang

2020

IEEE Access

View full text Add to dashboard Cite

Quality of Service (QoS) is applied to evaluate the satisfaction level of users using a service and it is a measure and evaluation of the service level of service providers. As one of the significant contents of grid technologies, the QoS has gradually become a focus of current Internet researches. The grid is a network infrastructure that can aggregate decentralized resources to form a higher-level distributed resource sharing environment; the highly dynamic performance presented by the grid system is caused by resource competition and task uncertainty and providing extraordinary QoS is one of the three criteria for evaluating the grid technologies. Bayesian network is a method of graphing knowledge and is a probabilistic model which can be calculated; data from various sources can be synthesized and comprehensively reasoned through this Bayesian network. On the basis of summarizing and analyzing previous research works, this paper expounds the development background, current situation and future challenges of Bayesian network technology, presents the studying status and existing problems of grid QoS trustworthiness evaluation, introduces network optimization analysis method and QoS trustworthiness evaluation algorithm, proposes the Bayesian network-based trustworthiness model, effectiveness function and grid QoS evaluation reasoning process, therefore, establishes grid QoS trustworthiness evaluation model and analyzes Bayesian networkbased QoS trustworthiness evaluation mechanism. The simulation results show that the proposed method can enhance the trustworthiness of service information and improve the rationality of service matching in a dynamic service grid environment. The study results of this paper provide a reference for the further researches on the grid QoS trustworthiness evaluation based on Bayesian network. INDEX TERMS Quality of Service (QoS), Bayesian network, trustworthiness evaluation, simulation experiment.

show abstract

“…We evaluate PredPRBA by conducting performance comparison with several other typical regression methods, such as Linear Regression (LR) (Jammalamadaka, 2003), K-nearest Neighbor Regression (KNNR) (Kramer, 2011; Kuang et al, 2019), SVM Regression (SVR) (Cherkassky and Ma, 2004), Decision Tree Regression (DTR) (Xu et al, 2005), Random Forest Regression (RFR) (Biau and Devroye, 2010) and Extremely Randomized Regression Trees (ERRT) (Geurts and Louppe, 2011). As shown in Table 6 , we find that PredPRBA performs significantly better than other regression methods for all classes of complexes.…”

Section: Resultsmentioning

confidence: 99%

PredPRBA: Prediction of Protein-RNA Binding Affinity Using Gradient Boosted Regression Trees

2019

View full text Add to dashboard Cite

Protein-RNA interactions play essential roles in many biological aspects. Quantifying the binding affinity of protein-RNA complexes is helpful to the understanding of protein-RNA recognition mechanisms and identification of strong binding partners. Due to experimentally measured protein-RNA binding affinity data available is still limited to date, there is a pressing demand for accurate and reliable computational approaches. In this paper, we propose a computational approach, PredPRBA, which can effectively predict protein-RNA binding affinity using gradient boosted regression trees. We build a dataset of protein-RNA binding affinity that includes 103 protein-RNA complex structures manually collected from related literature. Then, we generate 37 kinds of sequence and structural features and explore the relationship between the features and protein-RNA binding affinity. We find that the binding affinity mainly depends on the structure of RNA molecules. According to the type of RNA associated with proteins composed of the protein-RNA complex, we split the 103 protein-RNA complexes into six categories. For each category, we build a gradient boosted regression tree (GBRT) model based on the generated features. We perform a comprehensive evaluation for the proposed method on the binding affinity dataset using leave-one-out cross-validation. We show that PredPRBA achieves correlations ranging from 0.723 to 0.897 among six categories, which is significantly better than other typical regression methods and the pioneer protein-RNA binding affinity predictor SPOT-Seq-RNA. In addition, a user-friendly web server has been developed to predict the binding affinity of protein-RNA complexes. The PredPRBA webserver is freely available at .

show abstract

Predicting duration of traffic accidents based on cost-sensitive Bayesian network and weighted K-nearest neighbor

Cited by 75 publications

References 28 publications

Predicting uncertainty of machine learning models for modelling nitrate pollution of groundwater using quantile regression and UNEEC methods

Predicting uncertainty of machine learning models for modelling nitrate pollution of groundwater using quantile regression and UNEEC methods

Grid Quality of Service Trustworthiness Evaluation Based on Bayesian Network

PredPRBA: Prediction of Protein-RNA Binding Affinity Using Gradient Boosted Regression Trees

Contact Info

Product

Resources

About