Weighted Graph-Based Signal Temporal Logic Inference Using Neural Networks

Baharisangari, Nasim; Hirota, Kazuma; Yan, Ruixuan; Julius, A. Agung; Xu, Zhe

doi:10.1109/lcsys.2021.3138059

Cited by 3 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The weighted averages of the precision, recall, and f-score metrics were also conducted, and it was shown that our method and the XGBoost gave similar results of approximately 0.850 for all the metrics. The study in [36] presented a method based on neural networks to learn spatiotemporal knowledge in the form of weighted graph-based signal temporal logic (w-GSTL-NN) formulas. The experiments were conducted on 20% of the whole dataset.…”

Section: Resultsmentioning

confidence: 99%

“…As shown in Table 8, the proposed EK-stars method outperformed the recent studies in three scenarios based on the different training/test split ratios. When the 70:30 split ratio was applied, the average accuracy of the studies [28,29,36] was 81.28% while the EK-stars achieved an 85.05% accuracy. In the experiments with the 75:25 ratio, the studies in [25,38] were performed with an accuracy of 83.85% on average while the EK-stars concluded with 85.60%.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Rainfall Prediction Using an Ensemble Machine Learning Model Based on K-Stars

Tuysuzoglu

Birant

2023

Sustainability

View full text Add to dashboard Cite

Predicting the rainfall status of a region has a great impact on certain factors, such as arranging agricultural activities, enabling efficient water planning, and taking precautionary measures for possible disasters (flood/drought). Due to the seriousness of the subject, the timely and accurate prediction of rainfall is highly desirable and critical for environmentally sustainable development. In this study, an ensemble of K-stars (EK-stars) approach was proposed to predict the next-day rainfall status using meteorological data, such as the temperature, humidity, pressure, and sunshine, that were collected between the years 2007 and 2017 in Australia. This study also introduced the probability-based aggregating (pagging) approach when building and combining multiple classifiers for rainfall prediction. In the implementation of the EK-stars, different experimental setups were carried out, including the change of input parameter of the algorithm, the use of different methods in the pagging step, and whether the feature selection was performed or not. The EK-stars outperformed the original K-star algorithm and the recently proposed studies in terms of the classification accuracy by making predictions that were the closest to reality. This study shows that the proposed method is promising for generating accurate predictions for the sustainable development of environmental systems.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Rainfall Prediction Using an Ensemble Machine Learning Model Based on K-Stars

Tuysuzoglu

Birant

2023

Sustainability

View full text Add to dashboard Cite

show abstract

Learning Signal Temporal Logic through Neural Network for Interpretable Classification

Cai

Vasile

et al. 2023

2023 American Control Conference (ACC)

View full text Add to dashboard Cite

Time-series data can represent the behaviors of autonomous systems, such as drones and self-driving cars. The problem of binary and multi-class classification has received a lot of attention in this field. Neural networks represent a popular approach to classifying data; However, they lack interpretability, which poses a significant challenge in extracting meaningful information from them. Signal Temporal Logic (STL) is a formalism to describe the properties of timed behaviors. We propose a method that combines all of the above: neural networks that represent STL specifications for multi-class classification of time-series data. We offer two key contributions: 1) We introduce a notion of margin for multiclass classification, and 2) we introduce the use of STL-based attributes for enhancing the interpretability of the results. We evaluate our method on two datasets and compare with stateof-the-art baselines.

show abstract

Multi-Class Temporal Logic Neural Networks

Li,

Tron

2024

2024 American Control Conference (ACC)

View full text Add to dashboard Cite

Weighted Graph-Based Signal Temporal Logic Inference Using Neural Networks

Cited by 3 publications

References 10 publications

Rainfall Prediction Using an Ensemble Machine Learning Model Based on K-Stars

Rainfall Prediction Using an Ensemble Machine Learning Model Based on K-Stars

Learning Signal Temporal Logic through Neural Network for Interpretable Classification

Multi-Class Temporal Logic Neural Networks

Contact Info

Product

Resources

About