Nonlinear Autoregressive with Exogenous InputsNeural Network for Water Level Prediction

Sahagun, Mary Anne M.; Cruz, Jennifer C. Dela; Garcia, Ramon G.

doi:10.1109/hnicem.2018.8666406

Cited by 2 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These metric attempts to answer the question: When it is positive or yes, how often does it predict positive or yes? Mathematically: R = T P T P + FN (10) where: FN= false negative F-measure (F) is sometimes called F-score or F-measure. In a statistic analysis of binary classification, it ranges from 0 to 1, where 1 gives the best result.…”

Section: F Performance Metrics and Model Evaluationmentioning

confidence: 99%

“…Data mining is finding distinct patterns present in each dataset by a systematic processes. For the past couple of years, different data mining implementations have been applied in a wide variety of smart applications such as intelligent traffic systems (ITS) [1]- [4]; digital health [5]- [8]; disaster preparedness [9], [10]; and business economics [11], [12]. This type of technology can also be applied in education for improving learning such as distance learning [13] or predicting student achievement [14].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Based Selection of Incoming Engineering Freshmen in Higher Education Institution

Sahagun¹

2022

IJCDS

Self Cite

View full text Add to dashboard Cite

The Accrediting Agency of Chartered Colleges and Universities of the Philippines recommends through the university testing unit, a system to interpret and analyse entrance test results that may help direct and guide students in choosing a Baccalaureate degree to take in the college. While the present system of manually evaluating each of the freshman applicants is used, there is a need to adopt technological tools for faster and accurate analysis. Thus, the study presents machine learning methods of classifying freshmen applicants if they are qualified or not in the college of engineering and architecture. Specifically, determining if a freshmen applicant may succeed in the five engineering program at university. The study used classifiers such as Decision Tree, K-Nearest Neighbor (KNN), Decision Tree, and Support Vector Machine (SVM). A cross-validation of ten-fold model was used better accuracy of classifiers. The predicted models performed well, however, the Decision Tree classifier outputs a higher average accuracy and F1measure. The result shows that the classifier accurately classifies qualified and non-qualified engineering freshmen for program acceptance.

show abstract

Section: F Performance Metrics and Model Evaluationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Machine Learning Based Selection of Incoming Engineering Freshmen in Higher Education Institution

Sahagun¹

2022

IJCDS

Self Cite

View full text Add to dashboard Cite

show abstract

Comparative Evaluation of Water Level Forecasting Using IoT Sensor Data: Hydrodynamic Model SWMM vs. Machine Learning Models Based on NARX Framework

Frisk,

Johansson

2024

Water

View full text Add to dashboard Cite

This study evaluates the accuracy of water level forecasting using two approaches: the hydrodynamic model SWMM and machine learning (ML) models based on the Nonlinear Autoregressive with Exogenous Inputs (NARX) framework. SWMM offers a physically based modeling approach, while NARX is a data-driven method. Both models use real-time precipitation data, with their predictions compared against measurements from a network of IoT sensors in a stormwater management system. The results demonstrate that while both models provide effective forecasts, NARX models exhibit higher accuracy, with improved Nash–Sutcliffe Efficiency (NSE) coefficients and 33–37% lower mean absolute error (MAE) compared to SWMM. Despite these advantages, NARX models may struggle with limited data on extreme flooding events, where they could face accuracy challenges. Enhancements in SWMM modeling and calibration could reduce the performance gap, but the development of SWMM models requires substantial expertise and resources. In contrast, NARX models are generally more resource-efficient. Future research should focus on integrating both approaches by leveraging SWMM simulations to generate synthetic data, particularly for extreme weather events, to enhance the robustness of NARX and other ML models in real-world flood prediction scenarios.

show abstract

Nonlinear Autoregressive with Exogenous InputsNeural Network for Water Level Prediction

Cited by 2 publications

References 19 publications

Machine Learning Based Selection of Incoming Engineering Freshmen in Higher Education Institution

Machine Learning Based Selection of Incoming Engineering Freshmen in Higher Education Institution

Comparative Evaluation of Water Level Forecasting Using IoT Sensor Data: Hydrodynamic Model SWMM vs. Machine Learning Models Based on NARX Framework

Contact Info

Product

Resources

About