A Spatiotemporal Convolutional Gated Recurrent Unit Network for Mean Wave Period Field Forecasting

Mean wave period (MWP) is one of the key parameters affecting the design of marine facilities. Currently, there are two main methods, numerical and data-driven methods, for forecasting wave parameters, of which the latter are widely used. However, few studies have focused on MWP forecasting, and even fewer have investigated it with spatial and temporal information. In this study, correlations between ocean dynamic parameters are explored to obtain appropriate input features, significant wave height (SWH) and MWP. Subsequently, a data-driven approach, the convolution gated recurrent unit (Conv-GRU) model with spatiotemporal characteristics, is utilized to field forecast MWP with 1, 3, 6, 12, and 24-h lead times in the South China Sea. Six points at different locations and six consecutive moments at every 12-h intervals are selected to study the forecasting ability of the proposed model. The Conv-GRU model has a better performance than the single gated recurrent unit (GRU) model in terms of root mean square error (RMSE), the scattering index (SI), Bias, and the Pearson’s correlation coefficient (R). With the lead time increasing, the forecast effect shows a decreasing trend, specifically, the experiment displays a relatively smooth forecast curve and presents a great advantage in the short-term forecast of the MWP field in the Conv-GRU model, where the RMSE is 0.121 m for 1-h lead time.

Download Full-text

Novel Approach for Calibrating Freeway Highway Multi-Regimes Fundamental Diagram

Transportation Research Record Journal of the Transportation Research Board ◽

10.1177/0361198120930221 ◽

2020 ◽

Vol 2674 (9) ◽

pp. 561-574

Author(s):

Emmanuel Kidando ◽

Alican Karaer ◽

Boniphace Kutela ◽

Angela E. Kitali ◽

Ren Moses ◽

...

Keyword(s):

Traffic Flow ◽

Bayesian Model ◽

Potential Benefit ◽

Data Driven ◽

Fundamental Diagram ◽

Novel Approach ◽

Proposed Model ◽

Density Relationship ◽

Data Driven Approach ◽

Flow Variables

For almost a century, several models have been developed to calibrate the pairwise relationship between traffic flow variables, that is, speed, density, and flow. Multi-regime models are well known for being superior over single-regime models in fitting the speed–density relationship. However, in modeling multi-regime models, breakpoints that separate the regimes are visually established based on the subjective judgment of data characteristics. Thus, this study proposes a data-driven approach to estimate the breakpoints of multi-regime models. It applies the Bayesian model for calibrating multi-regime models (two and three-regime models) for fitting traffic flow fundamental diagram. Furthermore, the analysis presented accounts for the random characteristics associated with the flow. To demonstrate the application of the proposed algorithm, traffic flow data from Interstate 10 (I-10) freeway in Jacksonville, Florida, were used in the analysis. The results demonstrate the potential benefit of using the proposed model in calibrating the fundamental diagram. The proposed approach can also quantify uncertainty and encode prior knowledge about the breakpoints in the model if the model developer wishes.

Download Full-text

Clustering for Data-driven Unraveling Artificial Neural Networks

10.5753/eniac.2020.12160 ◽

2020 ◽

Author(s):

Felipe Farias ◽

Teresa Ludermir ◽

Carmelo Bastos-Filho

Keyword(s):

Neural Networks ◽

Statistical Significance ◽

Feature Space ◽

Data Driven ◽

P Value ◽

Proposed Model ◽

Data Driven Approach ◽

Benchmark Datasets ◽

Hidden Layer ◽

Fold Cross Validation

This work presents an investigation on how to define Neural Networks (NN) architectures adopting a data-driven approach using clustering to create sub-labels to facilitate the learning process and to discover the number of neurons needed to compose the layers. We also increase the depth of the model aiming to represent the samples better, the more in-depth it flows into the model. We hypothesize that the clustering process identifies sub-regions in the feature space in which the samples belonging to the same cluster have strong similarities. We used seven benchmark datasets to validate our hypothesis using 10-fold cross validation 3 times. The proposed model increased the performance, while never decreased it, with statistical significance considering the p-value $< 0.05$ in comparison with a Multi-Layer Perceptron with a single hidden layer with approximately the same number of parameters of the architectures found by our approach.

Download Full-text

Appointment Lead Time Policy Development to Improve Patient Access to Care

Applied Clinical Informatics ◽

10.4338/aci-2016-03-ra-0044 ◽

2016 ◽

Vol 07 (04) ◽

pp. 954-968 ◽

Cited By ~ 1

Author(s):

Sarah Bach ◽

Yu-Li Huang

Keyword(s):

Access To Care ◽

Health Care Providers ◽

Policy Development ◽

Lead Time ◽

Lead Times ◽

Patient Access ◽

Care Providers ◽

Data Driven Approach ◽

The Difference ◽

Improve Patient

Summary Background Patient access to care has been a known and continuing struggle for many health care providers. In spite of appointment lead time policies set by government or clinics, the problem persists. Justification for how lead time policies are determined is lacking. Objectives This paper proposed a data-driven approach for how to best set feasible appointment target lead times given a clinic’s capacity and appointment requests. Methods The proposed approach reallocates patient visits to minimize the deviation between actual appointment lead time and a feasible target lead time. A step-by-step algorithm was presented and demonstrated for return visit (RV) and new patient (NP) types from a Pediatric clinic excluding planned visits such as well-child exam and the same day urgent appointments. The steps are: 1. Obtain appointment requests; 2. Initialize a target lead time; 3. Set up an initial schedule; 4. Check the feasibility based on appointment availability; 5. Adjust schedule backward to fill appointment slots earlier than the target; 6. Adjust schedule forward for appointments not able to be scheduled earlier or on target to the later slots; 7. Trial different target lead times until the difference between earlier and later lead time is minimized. Results The results indicated a 59% lead time reduction for RVs and a 45% reduction for NPs. The lead time variation was reduced by 75% for both patient types. Additionally, the opportunity for the participating clinic to achieve their organization’s goal of a two-week lead time for RVs and a twoday lead time for NPs is discussed by adjusting capacity to increase one slot for NP and reduce one slot for RV. Conclusions The proposed approach and study findings may help clinics identify feasible appointment lead times. Citation: Huang Y, Bach SM. Appointment lead time policy development to improve patient access to care.

Download Full-text

Model and Data-Driven System Portfolio Selection Based on Value and Risk

Applied Sciences ◽

10.3390/app9081657 ◽

2019 ◽

Vol 9 (8) ◽

pp. 1657

Author(s):

Hechuan Wei ◽

Boyuan Xia ◽

Zhiwei Yang ◽

Zhexuan Zhou

Keyword(s):

Portfolio Selection ◽

Remaining Useful Life ◽

Pareto Set ◽

Data Driven ◽

Multiple Systems ◽

Proposed Model ◽

Driven System ◽

Data Driven Approach ◽

Overall Performance

System portfolio selection is a kind of tradeoff analysis and decision-making on multiple systems as a whole to fulfill the overall performance on the perspective of System of Systems (SoS). To avoid the subjectivity of traditional expert experience-dependent models, a model and data-driven approach is proposed to make an advance on the system portfolio selection. Two criteria of value and risk are used to indicate the quality of system portfolios. A capability gap model is employed to determine the value of system portfolios, with the weight information determined by correlation analysis. Then, the risk is represented by the remaining useful life (RUL), which is predicted by analyzing time series of system operational data. Next, based on the value and risk, an optimization model is proposed. Finally, a case with 100 candidate systems is studied under the scenario of anti-missile. By utilizing the Non-dominated Sorting Differential Evolution (NSDE) algorithm, a Pareto set with 200 individuals is obtained. Some characters of the Pareto set are analyzed by discussing the frequency of being selected and the association rules. Through the conclusion of the whole procedures, it can be proved that the proposed model and data-driven approach is feasible and effective for system portfolio selection.

Download Full-text

Data-driven malaria prevalence prediction in large densely populated urban holoendemic sub-Saharan West Africa

Scientific Reports ◽

10.1038/s41598-020-72575-6 ◽

2020 ◽

Vol 10 (1) ◽

Author(s):

Biobele J. Brown ◽

Petru Manescu ◽

Alexander A. Przybylski ◽

Fabio Caccioli ◽

Gbeminiyi Oyinloye ◽

...

Keyword(s):

Lead Time ◽

Healthcare Services ◽

Malaria Prevalence ◽

Data Driven ◽

Care Pathways ◽

Validation Data ◽

Data Driven Approach ◽

Sub Saharan ◽

Prediction Systems ◽

Current Systems

Abstract Over 200 million malaria cases globally lead to half-million deaths annually. The development of malaria prevalence prediction systems to support malaria care pathways has been hindered by lack of data, a tendency towards universal “monolithic” models (one-size-fits-all-regions) and a focus on long lead time predictions. Current systems do not provide short-term local predictions at an accuracy suitable for deployment in clinical practice. Here we show a data-driven approach that reliably produces one-month-ahead prevalence prediction within a densely populated all-year-round malaria metropolis of over 3.5 million inhabitants situated in Nigeria which has one of the largest global burdens of P. falciparum malaria. We estimate one-month-ahead prevalence in a unique 22-years prospective regional dataset of > 9 × 104 participants attending our healthcare services. Our system agrees with both magnitude and direction of the prediction on validation data achieving MAE ≤ 6 × 10–2, MSE ≤ 7 × 10–3, PCC (median 0.63, IQR 0.3) and with more than 80% of estimates within a (+ 0.1 to − 0.05) error-tolerance range which is clinically relevant for decision-support in our holoendemic setting. Our data-driven approach could facilitate healthcare systems to harness their own data to support local malaria care pathways.

Download Full-text

The skill of seasonal ensemble low-flow forecasts in the Moselle River for three different hydrological models

Hydrology and Earth System Sciences ◽

10.5194/hess-19-275-2015 ◽

2015 ◽

Vol 19 (1) ◽

pp. 275-291 ◽

Cited By ~ 39

Author(s):

M. C. Demirel ◽

M. J. Booij ◽

A. Y. Hoekstra

Keyword(s):

Lead Time ◽

Potential Evapotranspiration ◽

Data Driven ◽

Low Flow ◽

Lead Times ◽

Model Output ◽

Precipitation Data ◽

Hydrological Models ◽

Initial Model ◽

Meteorological Forcing

Abstract. This paper investigates the skill of 90-day low-flow forecasts using two conceptual hydrological models and one data-driven model based on Artificial Neural Networks (ANNs) for the Moselle River. The three models, i.e. HBV, GR4J and ANN-Ensemble (ANN-E), all use forecasted meteorological inputs (precipitation P and potential evapotranspiration PET), whereby we employ ensemble seasonal meteorological forecasts. We compared low-flow forecasts for five different cases of seasonal meteorological forcing: (1) ensemble P and PET forecasts; (2) ensemble P forecasts and observed climate mean PET; (3) observed climate mean P and ensemble PET forecasts; (4) observed climate mean P and PET and (5) zero P and ensemble PET forecasts as input for the models. The ensemble P and PET forecasts, each consisting of 40 members, reveal the forecast ranges due to the model inputs. The five cases are compared for a lead time of 90 days based on model output ranges, whereas the models are compared based on their skill of low-flow forecasts for varying lead times up to 90 days. Before forecasting, the hydrological models are calibrated and validated for a period of 30 and 20 years respectively. The smallest difference between calibration and validation performance is found for HBV, whereas the largest difference is found for ANN-E. From the results, it appears that all models are prone to over-predict runoff during low-flow periods using ensemble seasonal meteorological forcing. The largest range for 90-day low-flow forecasts is found for the GR4J model when using ensemble seasonal meteorological forecasts as input. GR4J, HBV and ANN-E under-predicted 90-day-ahead low flows in the very dry year 2003 without precipitation data. The results of the comparison of forecast skills with varying lead times show that GR4J is less skilful than ANN-E and HBV. Overall, the uncertainty from ensemble P forecasts has a larger effect on seasonal low-flow forecasts than the uncertainty from ensemble PET forecasts and initial model conditions.

Download Full-text