This page has only limited features, please log in for full access.

Unclaimed
Saerom Park
Department of Convergence Security Engineering Sungshin University Korea

Honors and Awards

The user has no records in this section


Career Timeline

The user has no records in this section.


Short Biography

The user biography is not available.
Following
Followers
Co Authors
The list of users this user is following is empty.
Following: 0 users

Feed

Letter
Published: 31 December 2020 in Electronics Letters
Reads 0
Downloads 0

The authors proposed a privacy‐preserving evaluation algorithm for support vector clustering with a fully homomorphic encryption. The proposed method assigns clustering labels to encrypted test data with an encrypted support function. This method inherits the advantageous properties of support vector clustering, which is naturally inductive to cluster new test data from complex distributions. The authors efficiently implemented the proposed method with elaborate packing of the plaintexts and avoiding non‐polynomial operations that are not friendly to homomorphic encryption. These experimental results showed that the proposed model is effective in terms of clustering performance and has robustness against the error that occurs from homomorphic evaluation and approximate operations.

ACS Style

J. Byun; J. Lee; S. Park. Privacy‐preserving evaluation for support vector clustering. Electronics Letters 2020, 57, 61 -64.

AMA Style

J. Byun, J. Lee, S. Park. Privacy‐preserving evaluation for support vector clustering. Electronics Letters. 2020; 57 (2):61-64.

Chicago/Turabian Style

J. Byun; J. Lee; S. Park. 2020. "Privacy‐preserving evaluation for support vector clustering." Electronics Letters 57, no. 2: 61-64.

Journal article
Published: 01 November 2019 in Neural Networks
Reads 0
Downloads 0

Learning document representation is important in applying machine learning algorithms for sentiment analysis. Distributed representation learning models of words and documents, one of neural language models, have overcome some limits of vector space models such as bag-of-words model and have been utilized successively in many natural language processing tasks including sentiment analysis. However, because such models learn the embeddings only with a context-based objective, it is hard for embeddings to reflect the sentiment of texts. In this research, we address this problem by introducing a semi-supervised sentiment-discriminative objective using partial sentiment information of documents. Our method not only reflects the partial sentiment information, but also preserves local structures induced from original distributed representation learning objectives by considering only sentiment relationships between neighboring documents. Using real-world datasets, the proposed method has been validated by sentiment visualization and classification tasks. The visualization results of Amazon review datasets demonstrate the enhancement of the sentiment class separation when document representations of our proposed method are compared to other methods. Sentiment prediction from our representations also appears to be consistently superior to other representations in both Amazon and Yelp datasets. This work can be extended to develop effective document embeddings applied to other discriminative tasks.

ACS Style

Saerom Park; Jaewook Lee; Kyoungok Kim. Semi-supervised distributed representations of documents for sentiment analysis. Neural Networks 2019, 119, 139 -150.

AMA Style

Saerom Park, Jaewook Lee, Kyoungok Kim. Semi-supervised distributed representations of documents for sentiment analysis. Neural Networks. 2019; 119 ():139-150.

Chicago/Turabian Style

Saerom Park; Jaewook Lee; Kyoungok Kim. 2019. "Semi-supervised distributed representations of documents for sentiment analysis." Neural Networks 119, no. : 139-150.

Journal article
Published: 25 June 2019 in Sustainability
Reads 0
Downloads 0

Developing a robust and sustainable system is an important problem in which deep learning models are used in real-world applications. Ensemble methods combine diverse models to improve performance and achieve robustness. The analysis of time series data requires dealing with continuously incoming instances; however, most ensemble models suffer when adapting to a change in data distribution. Therefore, we propose an on-line ensemble deep learning algorithm that aggregates deep learning models and adjusts the ensemble weight based on loss value in this study. We theoretically demonstrate that the ensemble weight converges to the limiting distribution, and, thus, minimizes the average total loss from a new regret measure based on adversarial assumption. We also present an overall framework that can be applied to analyze time series. In the experiments, we focused on the on-line phase, in which the ensemble models predict the binary class for the simulated data and the financial and non-financial real data. The proposed method outperformed other ensemble approaches. Moreover, our method was not only robust to the intentional attacks but also sustainable in data distribution changes. In the future, our algorithm can be extended to regression and multiclass classification problems.

ACS Style

Hyungjin Ko; Jaewook Lee; Junyoung Byun; BumHo Son; Saerom Park. Loss-Driven Adversarial Ensemble Deep Learning for On-Line Time Series Analysis. Sustainability 2019, 11, 3489 .

AMA Style

Hyungjin Ko, Jaewook Lee, Junyoung Byun, BumHo Son, Saerom Park. Loss-Driven Adversarial Ensemble Deep Learning for On-Line Time Series Analysis. Sustainability. 2019; 11 (12):3489.

Chicago/Turabian Style

Hyungjin Ko; Jaewook Lee; Junyoung Byun; BumHo Son; Saerom Park. 2019. "Loss-Driven Adversarial Ensemble Deep Learning for On-Line Time Series Analysis." Sustainability 11, no. 12: 3489.

Validation study
Published: 17 October 2018 in Computational Intelligence and Neuroscience
Reads 0
Downloads 0

This paper describes a new image generation algorithm based on generative adversarial network. With an information-theoretic extension to the autoencoder-based discriminator, this new algorithm is able to learn interpretable representations from the input images. Our model not only adversarially minimizes the Wasserstein distance-based losses of the discriminator and generator but also maximizes the mutual information between small subset of the latent variables and the observation. We also train our model with proportional control theory to keep the equilibrium between the discriminator and the generator balanced, and as a result, our generative adversarial network can mitigate the convergence problem. Through the experiments on real images, we validate our proposed method, which can manipulate the generated images as desired by controlling the latent codes of input variables. In addition, the visual qualities of produced images are effectively maintained, and the model can stably converge to the equilibrium. However, our model has a difficulty in learning disentangling factors because our model does not regularize the independence between the interpretable factors. Therefore, in the future, we will develop a generative model that can learn disentangling factors.

ACS Style

Junghoon Hah; Woojin Lee; Jaewook Lee; Saerom Park. Information-Based Boundary Equilibrium Generative Adversarial Networks with Interpretable Representation Learning. Computational Intelligence and Neuroscience 2018, 2018, 1 -14.

AMA Style

Junghoon Hah, Woojin Lee, Jaewook Lee, Saerom Park. Information-Based Boundary Equilibrium Generative Adversarial Networks with Interpretable Representation Learning. Computational Intelligence and Neuroscience. 2018; 2018 ():1-14.

Chicago/Turabian Style

Junghoon Hah; Woojin Lee; Jaewook Lee; Saerom Park. 2018. "Information-Based Boundary Equilibrium Generative Adversarial Networks with Interpretable Representation Learning." Computational Intelligence and Neuroscience 2018, no. : 1-14.