Density-Based Core Support Extraction for Non-stationary Environments with Extreme Verification Latency

Ferreira, Raul Sena; Silva, Bruno M. A. da; Teixeira, Wendell W.; Zimbrão, Geraldo; Alvim, Leandro G.M.

doi:10.1109/bracis.2018.00039

Cited by 4 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, expanding the prediction horizon to N p > 1 should present better dispatch strategies and needs more experimental tests. Finally, we highlight some directions for further research: 1)Density approaches aiming to reduce the bias of the learning model induced by the similar customer's calls contained in the stream [Ferreira et al 2018a]; 2)Since some characteristics of this real-time dataset are non-stationary, learning models for concept-drift can improve the results [Ferreira et al 2018b]; and 3)Development of better MPC objective function with other assumptions such as the total time that a customer does not have energy by month and the customer's location.…”

Section: Discussionmentioning

confidence: 99%

RDI: A Real-time Decision Support System Applied to Dispatch Decision Problem

Ferreira¹,

Pont²,

Silva³

et al. 2018

Anais Da v Escola Regional De Sistemas De Informação Do Rio De Janeiro

Self Cite

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

RDI: A Real-time Decision Support System Applied to Dispatch Decision Problem

Ferreira¹,

Pont²,

Silva³

et al. 2018

Anais Da v Escola Regional De Sistemas De Informação Do Rio De Janeiro

Self Cite

View full text Add to dashboard Cite

“…The choice of k represents a trade-off between accuracy in the training set and the amount of memory required to store the samples to be used at runtime. Previous works showed that such density estimation selection can discard up to 90% of the original dataset without a drastic performance drop [9]. Therefore, in this work, we chose k = 10% of the training set.…”

Section: Monitor Buildingmentioning

confidence: 99%

SENA: Similarity-Based Error-Checking of Neural Activations

Ferreira,

Guerin,

Guiochet

et al. 2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

In this work, we propose SENA, a run-time monitor focused on detecting unreliable predictions from machine learning (ML) classifiers. The main idea is that instead of trying to detect when an image is out-of-distribution (OOD), which will not always result in a wrong output, we focus on detecting if the prediction from the ML model is not reliable, which will most of the time result in a wrong output, independently of whether it is in-distribution (ID) or OOD. The verification is done by checking the similarity between the neural activations of an incoming input and a set of representative neural activations recorded during training. SENA uses information from true-positive and false-negative examples collected during training to verify if a prediction is reliable or not. Our approach achieves results comparable to state-of-the-art solutions without requiring any prior OOD information and without hyperparameter tuning. Besides, the code is publicly available for easy reproducibility at https://github.com/raulsenaferreira/SENA.

show abstract