Taesup Moon

Taesup Moon


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2020 in Environmental Pollution
Verified
Journal Article
Closed access
YPYongbee Park
Yongbee Park
BKByungjoon Kwon
Byungjoon Kwon
JHJuyeon Heo
Juyeon Heo
XHXuefei Hu
Xuefei Hu
Yang LiuYang Liu
Yang Liu
TMTaesup Moon
Taesup Moon

17 July 2019 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
CSChangho Shin
Changho Shin
SJSunghwan Joo
Sunghwan Joo
JYJaeryun Yim
Jaeryun Yim
HLHyoseop Lee
Hyoseop Lee
TMTaesup Moon
Taesup Moon
WRWonjong Rhee
Wonjong Rhee
Non-intrusive load monitoring (NILM), also known as energy disaggregation, is a blind source separation problem where a household’s aggregate electricity consumption is broken down into electricity usages of individual appliances. In this way, the cost and trouble of installing many measurement devices over numerous household appliances can be avoided, and only one device needs to be installed. The problem has been well-known since Hart’s seminal paper in 1992, and recently significant performance improvements have been achieved by adopting deep networks. In this work, we focus on the idea that appliances have on/off states, and develop a deep network for further performance improvements. Specifically, we propose a subtask gated network that combines the main regression network with an on/off classification subtask network. Unlike typical multitask learning algorithms where multiple tasks simply share the network parameters to take advantage of the relevance among tasks, the subtask gated network multiply the main network’s regression output with the subtask’s classification probability. When standby-power is additionally learned, the proposed solution surpasses the state-of-the-art performance for most of the benchmark cases. The subtask gated network can be very effective for any problem that inherently has on/off states.

27 July 2017 in PLOS ONE
Verified
Journal Article
Open access
PDF file
BLByunghan Lee
Byunghan Lee
TMTaesup Moon
Taesup Moon
SYSungroh Yoon
Sungroh Yoon
TWTsachy Weissman
Tsachy Weissman
We consider the correction of errors from nucleotide sequences produced by next-generation targeted amplicon sequencing. The next-generation sequencing (NGS) platforms can provide a great deal of sequencing data thanks to their high throughput, but the associated error rates often tend to be high. Denoising in high-throughput sequencing has thus become a crucial process for boosting the reliability of downstream analyses. Our methodology, named DUDE-Seq, is derived from a general setting of reconstructing finite-valued source data corrupted by a discrete memoryless channel and effectively corrects substitution and homopolymer indel errors, the two major types of sequencing errors in most high-throughput targeted amplicon sequencing platforms. Our experimental studies with real and simulated datasets suggest that the proposed DUDE-Seq not only outperforms existing alternatives in terms of error-correction capability and time efficiency, but also boosts the reliability of downstream analyses. Further, the flexibility of DUDE-Seq enables its robust application to different sequencing platforms and analysis pipelines by simple updates of the noise model. DUDE-Seq is available at http://data.snu.ac.kr/pub/dude-seq.

24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
SCSungmin Cha
Sungmin Cha
SCSungjun Cho
Sungjun Cho
DHDasol Hwang
Dasol Hwang
HLHonglak Lee
Honglak Lee
TMTaesup Moon
Taesup Moon
MLMoontae Lee
Moontae Lee
Since the recent advent of regulations for data protection (e.g., the General Data Protection Regulation), there has been increasing demand in deleting information learned from sensitive data in pre-trained models without retraining from scratch. The inherent vulnerability of neural networks towards adversarial attacks and unfairness also calls for a robust method to remove or correct information in an instance-wise fashion, while retaining the predictive performance across remaining data. To this end, we consider instance-wise unlearning, of which the goal is to delete information on a set of instances from a pre-trained model, by either misclassifying each instance away from its original prediction or relabeling the instance to a different label. We also propose two methods that reduce forgetting on the remaining data: 1) utilizing adversarial examples to overcome forgetting at the representation-level and 2) leveraging weight importance metrics to pinpoint network parameters guilty of propagating unwanted information. Both methods only require the pre-trained model and data instances to forget, allowing painless application to real-life settings where the entire training set is unavailable. Through extensive experimentation on various image classification benchmarks, we show that our approach effectively preserves knowledge of remaining data while unlearning given instances in both single-task and continual unlearning scenarios.

1 November 2021 in Hearing Research
Verified
Journal Article
Closed access
SLSang-Yeon Lee
Sang-Yeon Lee
MCMunyoung Chang
Munyoung Chang
BKByungjoon Kwon
Byungjoon Kwon
BCByung Yoon Choi
Byung Yoon Choi
JKJa-Won Koo
Ja-Won Koo
JSJae-Jin Song
Jae-Jin Song

12 February 2021 in Electronics
Verified
Journal Article
Open access
PDF file
Jinwoong LeeJinwoong Lee
Jinwoong Lee
TPTaeeon Park
Taeeon Park
HAHongjoon Ahn
Hongjoon Ahn
JKJihwan Kwak
Jihwan Kwak
TMTaesup Moon
Taesup Moon
Changhwan ShinChanghwan Shin
Changhwan Shin
As the physical size of MOSFET has been aggressively scaled-down, the impact of process-induced random variation (RV) should be considered as one of the device design considerations of MOSFET. In this work, an artificial neural network (ANN) model is developed to investigate the effect of line-edge roughness (LER)-induced random variation on the input/output transfer characteristics (e.g., off-state leakage current (Ioff), subthreshold slope (SS), saturation drain current (Id,sat), linear drain current (Id,lin), saturation threshold voltage (Vth,sat), and linear threshold voltage (Vth,lin)) of 5 nm FinFET. Hence, the prediction model was divided into two phases, i.e., “Predict Vth” and “Model Vth”. In the former, LER profiles were only used as training input features, and two threshold voltages (i.e., Vth,sat and Vth,lin) were target variables. In the latter, however, LER profiles and the two threshold voltages were used as training input features. The final prediction was then made by feeding the output of the first model to the input of the second model. The developed models were quantitatively evaluated by the Earth Mover Distance (EMD) between the target variables from the TCAD simulation tool and the predicted variables of the ANN model, and we confirm both the prediction accuracy and time-efficiency of our model.