Distance-based Probabilistic Data Augmentation for Synthetic Minority Oversampling

Goodman, John M.; Sarkani, Sharham; Mazzuchi, Thomas

doi:10.1145/3510834

Cited by 6 publications

(3 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Decomposition methods feature using decomposition techniques such as empirical mode decomposition to generate new data that preserves the information of the original data [93]. Statistical generative methods employ modeling the dynamics of data using statistical models based on the data [94]. Learning-based methods feature modeling the dynamics of data, primarily through AI techniques such as GAN [95].…”

Section: A Uncertainty Of Informationmentioning

confidence: 99%

A Survey and Perspective on Industrial Cyber-Physical Systems (ICPS): From ICPS to AI-Augmented ICPS

Chae,

Lee,

Jang

et al. 2023

Trans. Ind. Cyb-Phy. Sys.

View full text Add to dashboard Cite

Digital Transformation integrates information technology across a broad spectrum of industrial sectors. Industrial Cyber-Physical Systems (ICPS) play a vital role in this transformation by harmonizing machinery, production, logistics, and societal needs through innovative information technologies. This paper investigates the adoption of industrial artificial intelligence (industrial AI) as a methodology for effective ICPS design, introducing AI-Augmented ICPS (AICPS). The study conducts a survey, focusing on the components and interactions of AICPS. We propose design considerations for the implementation of AICPS and investigate the application of cutting-edge industrial AI techniques in each interaction. From the standpoint of AI augmentation, this paper offers insights by identifying key perspectives, including uncertainty of information, safety of AI, explainability of AI, human-societal interactive ICPS, and standardization of industrial AI. This paper aims to enhance understanding of AICPS and lay the groundwork for integrating independent industrial AI techniques into ICPS.

show abstract

Section: A Uncertainty Of Informationmentioning

confidence: 99%

A Survey and Perspective on Industrial Cyber-Physical Systems (ICPS): From ICPS to AI-Augmented ICPS

Chae,

Lee,

Jang

et al. 2023

Trans. Ind. Cyb-Phy. Sys.

View full text Add to dashboard Cite

show abstract

“…It is clear that the sample associated with C 1 landing within the boundary of the closed The mechanics of candidate acceptance partially mirrors that of candidate generation, i.e., we look to find candidates whose kNN distance to the training set is sufficiently greater than the kNN distances within the training set. The mathematical justification for this observation [40] follows from divergence between the distribution of closed set sample f (X ) and the distribution of synthetic anomalies f (A)…”

Section: A Candidate Synthetic Anomaly Generationmentioning

confidence: 99%

A Generative Approach to Open Set Recognition Using Distance-Based Probabilistic Anomaly Augmentation

2022

View full text Add to dashboard Cite

Machine learning (ML) algorithms that are used in decision support (DS) and autonomous systems commonly train on labeled categorical samples from a closed set. This, however, poses a problem for deployed DS and autonomous systems when they encounter an anomalous pattern that did not originate from the closed set distribution used for training. In this case, the ML algorithm that was trained only on closed set samples may erroneously identify an anomalous pattern as having originated from one of the categories in the closed set, sometimes with very high confidence. In this paper, we consider the problem of unknown pattern recognition from a generative perspective in which additional synthetic training samples that represent anomalies are added to the training data. These synthetic samples are generated to optimally balance the desire to place anomalies all along the boundary of the training set in feature space, while not adversely effecting core classification performance on the test set. We demonstrate the efficacy of distance-based probabilistic anomaly augmentation (DPAA) that is proposed in this paper for a diverse set of applications such as character recognition and intrusion detection, and compare its combined classification and identification performance to both recent open set and more traditional novelty detection approaches. INDEX TERMSMachine learning, outlier and novelty detection, open set recognition, anomalies, generative and discriminative architectures.

show abstract

“…However, this approach may result in over-fitting by over-emphasizing noisy minority samples. The second approach for increasing the number of minority class samples is to generate new synthetic minority class samples (Abd Elrahman & Abraham, 2013;Chawla et al, 2002;Wan et al, 2017;Goodman et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

A theoretical distribution analysis of synthetic minority oversampling technique (SMOTE) for imbalanced learning

2023

View full text Add to dashboard Cite

Class imbalance occurs when the class distribution is not equal. Namely, one class is under-represented (minority class), and the other class has significantly more samples in the data (majority class). The class imbalance problem is prevalent in many real world applications. Generally, the under-represented minority class is the class of interest. The synthetic minority over-sampling technique (SMOTE) method is considered the most prominent method for handling unbalanced data. The SMOTE method generates new synthetic data patterns by performing linear interpolation between minority class samples and their K nearest neighbors. However, the SMOTE generated patterns do not necessarily conform to the original minority class distribution. This paper develops a novel theoretical analysis of the SMOTE method by deriving the probability distribution of the SMOTE generated samples. To the best of our knowledge, this is the first work deriving a mathematical formulation for the SMOTE patterns’ probability distribution. This allows us to compare the density of the generated samples with the true underlying class-conditional density, in order to assess how representative the generated samples are. The derived formula is verified by computing it on a number of densities versus densities computed and estimated empirically.

show abstract

Distance-based Probabilistic Data Augmentation for Synthetic Minority Oversampling

Cited by 6 publications

References 46 publications

A Survey and Perspective on Industrial Cyber-Physical Systems (ICPS): From ICPS to AI-Augmented ICPS

A Survey and Perspective on Industrial Cyber-Physical Systems (ICPS): From ICPS to AI-Augmented ICPS

A Generative Approach to Open Set Recognition Using Distance-Based Probabilistic Anomaly Augmentation

A theoretical distribution analysis of synthetic minority oversampling technique (SMOTE) for imbalanced learning

Contact Info

Product

Resources

About