Search

Your search keyword '"Jung, In Young"' showing total 14,262 results
Start Over Author "Jung, In Young"
14,262 results on '"Jung, In Young"'

1. BTS: Bridging Text and Sound Modalities for Metadata-Aided Respiratory Sound Classification

Author

Kim, June-Woo, Toikkanen, Miika, Choi, Yera, Moon, Seoung-Eun, and Jung, Ho-Young

Subjects
Computer Science - Sound, Computer Science - Artificial Intelligence, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

Respiratory sound classification (RSC) is challenging due to varied acoustic signatures, primarily influenced by patient demographics and recording environments. To address this issue, we introduce a text-audio multimodal model that utilizes metadata of respiratory sounds, which provides useful complementary information for RSC. Specifically, we fine-tune a pretrained text-audio multimodal model using free-text descriptions derived from the sound samples' metadata which includes the gender and age of patients, type of recording devices, and recording location on the patient's body. Our method achieves state-of-the-art performance on the ICBHI dataset, surpassing the previous best result by a notable margin of 1.17%. This result validates the effectiveness of leveraging metadata and respiratory sound samples in enhancing RSC performance. Additionally, we investigate the model performance in the case where metadata is partially unavailable, which may occur in real-world clinical setting., Comment: Accepted INTERSPEECH 2024

Published
2024

2. Contrastive and Consistency Learning for Neural Noisy-Channel Model in Spoken Language Understanding

Author

Kim, Suyoung, Hwang, Jiyeon, and Jung, Ho-Young

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence
Abstract

Recently, deep end-to-end learning has been studied for intent classification in Spoken Language Understanding (SLU). However, end-to-end models require a large amount of speech data with intent labels, and highly optimized models are generally sensitive to the inconsistency between the training and evaluation conditions. Therefore, a natural language understanding approach based on Automatic Speech Recognition (ASR) remains attractive because it can utilize a pre-trained general language model and adapt to the mismatch of the speech input environment. Using this module-based approach, we improve a noisy-channel model to handle transcription inconsistencies caused by ASR errors. We propose a two-stage method, Contrastive and Consistency Learning (CCL), that correlates error patterns between clean and noisy ASR transcripts and emphasizes the consistency of the latent features of the two transcripts. Experiments on four benchmark datasets show that CCL outperforms existing methods and improves the ASR robustness in various noisy environments. Code is available at https://github.com/syoung7388/CCL., Comment: Accepted NAACL 2024

Published
2024

3. RepAugment: Input-Agnostic Representation-Level Augmentation for Respiratory Sound Classification

Author

Kim, June-Woo, Toikkanen, Miika, Bae, Sangmin, Kim, Minseok, and Jung, Ho-Young

Subjects
Computer Science - Sound, Computer Science - Artificial Intelligence, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

Recent advancements in AI have democratized its deployment as a healthcare assistant. While pretrained models from large-scale visual and audio datasets have demonstrably generalized to this task, surprisingly, no studies have explored pretrained speech models, which, as human-originated sounds, intuitively would share closer resemblance to lung sounds. This paper explores the efficacy of pretrained speech models for respiratory sound classification. We find that there is a characterization gap between speech and lung sound samples, and to bridge this gap, data augmentation is essential. However, the most widely used augmentation technique for audio and speech, SpecAugment, requires 2-dimensional spectrogram format and cannot be applied to models pretrained on speech waveforms. To address this, we propose RepAugment, an input-agnostic representation-level augmentation technique that outperforms SpecAugment, but is also suitable for respiratory sound classification with waveform pretrained models. Experimental results show that our approach outperforms the SpecAugment, demonstrating a substantial improvement in the accuracy of minority disease classes, reaching up to 7.14%., Comment: Accepted EMBC 2024

Published
2024

9. Stethoscope-guided Supervised Contrastive Learning for Cross-domain Adaptation on Respiratory Sound Classification

Author

Kim, June-Woo, Bae, Sangmin, Cho, Won-Yang, Lee, Byungjo, and Jung, Ho-Young

Subjects
Computer Science - Sound, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

Despite the remarkable advances in deep learning technology, achieving satisfactory performance in lung sound classification remains a challenge due to the scarcity of available data. Moreover, the respiratory sound samples are collected from a variety of electronic stethoscopes, which could potentially introduce biases into the trained models. When a significant distribution shift occurs within the test dataset or in a practical scenario, it can substantially decrease the performance. To tackle this issue, we introduce cross-domain adaptation techniques, which transfer the knowledge from a source domain to a distinct target domain. In particular, by considering different stethoscope types as individual domains, we propose a novel stethoscope-guided supervised contrastive learning approach. This method can mitigate any domain-related disparities and thus enables the model to distinguish respiratory sounds of the recording variation of the stethoscope. The experimental results on the ICBHI dataset demonstrate that the proposed methods are effective in reducing the domain dependency and achieving the ICBHI Score of 61.71%, which is a significant improvement of 2.16% over the baseline., Comment: accepted to ICASSP 2024

Published
2023

10. Balloon-expandable cobalt chromium stent versus self-expandable nitinol stent for the Atherosclerotic Iliac Arterial Disease (SENS-ILIAC Trial) Trial: a randomized controlled trial

Author

Choi, Woong Gil, Rha, Seung-Woon, Choi, Byoung Geol, Park, Soohyung, Kim, Ji Bak, Kang, Dong Oh, Choi, Cheol Ung, Seo, Yong Sung, Cho, Yoon Hyung, Park, Sang Ho, Lee, Seung Jin, Ko, Young Guk, Her, Ae-Young, Kim, Sang Min, Kim, Ki Chang, Cho, Jang Hyun, Kang, Won Yu, Kim, Joo Han, Kim, Min Woong, Kim, Do Hoi, Bae, Jang Ho, Ahn, Ji Hoon, Jo, Sang Cheol, Seo, Jae Bin, Jung, Woo Young, and Park, Sang Min

Published
2024
Full Text
View/download PDF

13. Adversarial Fine-tuning using Generated Respiratory Sound to Address Class Imbalance

Author

Kim, June-Woo, Yoon, Chihyeon, Toikkanen, Miika, Bae, Sangmin, and Jung, Ho-Young

Subjects
Computer Science - Sound, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

Deep generative models have emerged as a promising approach in the medical image domain to address data scarcity. However, their use for sequential data like respiratory sounds is less explored. In this work, we propose a straightforward approach to augment imbalanced respiratory sound data using an audio diffusion model as a conditional neural vocoder. We also demonstrate a simple yet effective adversarial fine-tuning method to align features between the synthetic and real respiratory sound samples to improve respiratory sound classification performance. Our experimental results on the ICBHI dataset demonstrate that the proposed adversarial fine-tuning is effective, while only using the conventional augmentation method shows performance degradation. Moreover, our method outperforms the baseline by 2.24% on the ICBHI Score and improves the accuracy of the minority classes up to 26.58%. For the supplementary material, we provide the code at https://github.com/kaen2891/adversarial_fine-tuning_using_generated_respiratory_sound., Comment: accepted in NeurIPS 2023 Workshop on Deep Generative Models for Health (DGM4H)

Published
2023

33. Real-world outcomes of third-line immune checkpoint inhibitors versus irinotecan-based chemotherapy in patients with advanced gastric cancer: a Korean, multicenter study (KCSG ST22-06)

Author

Lim, Sung Hee, Lee, Keun-Wook, Kim, Jae-Joon, Im, Hyeon-Su, Kim, In-Ho, Han, Hye Sook, Koo, Dong-Hoe, Cho, Jang Ho, Maeng, Chi Hoon, Lee, Min-Young, Lee, Hyo Jin, Kim, Jwa Hoon, Park, Sang Gon, Jung, Joo Young, Shin, Seong-Hoon, Kim, Ki Hyang, Kim, Hyeyeong, Oh, So Yeon, Kang, Minsu, Jung, Minkyu, and Rha, Sun Young

Published
2024
Full Text
View/download PDF

36. FOXO1 is a master regulator of memory programming in CAR T cells

Author

Doan, Alexander E., Mueller, Katherine P., Chen, Andy Y., Rouin, Geoffrey T., Chen, Yingshi, Daniel, Bence, Lattin, John, Markovska, Martina, Mozarsky, Brett, Arias-Umana, Jose, Hapke, Robert, Jung, In-Young, Wang, Alice, Xu, Peng, Klysz, Dorota, Zuern, Gabrielle, Bashti, Malek, Quinn, Patrick J., Miao, Zhuang, Sandor, Katalin, Zhang, Wenxi, Chen, Gregory M., Ryu, Faith, Logun, Meghan, Hall, Junior, Tan, Kai, Grupp, Stephan A., McClory, Susan E., Lareau, Caleb A., Fraietta, Joseph A., Sotillo, Elena, Satpathy, Ansuman T., Mackall, Crystal L., and Weber, Evan W.

Published
2024
Full Text
View/download PDF

41. Light sterile neutrino and leptogenesis

Author

Jung, Ki-Young and Siyeon, Kim

Subjects
High Energy Physics - Phenomenology
Abstract

We studied models of leptogenesis where three right-handed Majorana neutrinos are involved and the minimal-extended seesaw mechanism including an additional singlet field produces four light neutrinos. This study shows that the type of mass ordering and heavy Majorana scales can be determined by inputting the simplest orthogonal matrix into the Casas-Ibarra(CI) representation of seesaw. The CP asymmetry produced from the decays of heavy neutrinos and the dilution mass are predicted in terms of the mass and mixing elements of the fourth neutrino. Upon the choice of CI matrix, the existence of a light sterile neutrino is required to explain the high-energy lepton asymmetry in light of phenomenological measurements. Although there are several free parameters attributable to an additional neutrino, the model can be in part constrained by low-energy experiments such as sterile neutrino searches and neutrinoless double-beta decays, as well as the observed baryon asymmetry in the universe., Comment: 23 pages, 7 figures

Published
2022
Full Text
View/download PDF

42. Winters are changing: snow effects on Arctic and alpine tundra ecosystems1

Author

Rixen, Christian, Høye, Toke Thomas, Macek, Petr, Aerts, Rien, Alatalo, Juha M, Anderson, Jill T, Arnold, Pieter A, Barrio, Isabel C, Bjerke, Jarle W, Björkman, Mats P, Blok, Daan, Blume-Werry, Gesche, Boike, Julia, Bokhorst, Stef, Carbognani, Michele, Christiansen, Casper T, Convey, Peter, Cooper, Elisabeth J, Cornelissen, J Hans C, Coulson, Stephen J, Dorrepaal, Ellen, Elberling, Bo, Elmendorf, Sarah C, Elphinstone, Cassandra, Forte, T’ai GW, Frei, Esther R, Geange, Sonya R, Gehrmann, Friederike, Gibson, Casey, Grogan, Paul, Halbritter, Aud Helen, Harte, John, Henry, Gregory HR, Inouye, David W, Irwin, Rebecca E, Jespersen, Gus, Jónsdóttir, Ingibjörg Svala, Jung, Ji Young, Klinges, David H, Kudo, Gaku, Lämsä, Juho, Lee, Hanna, Lembrechts, Jonas J, Lett, Signe, Lynn, Joshua Scott, Mann, Hjalte MR, Mastepanov, Mikhail, Morse, Jennifer, Myers-Smith, Isla H, Olofsson, Johan, Paavola, Riku, Petraglia, Alessandro, Phoenix, Gareth K, Semenchuk, Philipp, Siewert, Matthias B, Slatyer, Rachel, Spasojevic, Marko J, Suding, Katharine, Sullivan, Patrick, Thompson, Kimberly L, Väisänen, Maria, Vandvik, Vigdis, Venn, Susanna, Walz, Josefine, Way, Robert, Welker, Jeffrey M, Wipf, Sonja, and Zong, Shengwei

Subjects
review, tundra, ground temperatures, snow experiments, ITEX
Abstract

Snow is an important driver of ecosystem processes in cold biomes. Snow accumulation determines ground temperature, light conditions, and moisture availability during winter. It also affects the growing season’s start and end, and plant access to moisture and nutrients. Here, we review the current knowledge of the snow cover’s role for vegetation, plant-animal interactions, permafrost conditions, microbial processes, and biogeochemical cycling. We also compare studies of natural snow gradients with snow experimental manipulation studies to assess time scale difference of these approaches. The number of tundra snow studies has increased considerably in recent years, yet we still lack a comprehensive overview of how altered snow conditions will affect these ecosystems. Specifically, we found a mismatch in the timing of snowmelt when comparing studies of natural snow gradients with snow manipulations. We found that snowmelt timing achieved by snow addition and snow removal manipulations (average 7.9 days advance and 5.5 days delay, respectively) were substantially lower than the temporal variation over natural spatial gradients within a given year (mean range 56 days) or among years (mean range 32 days). Differences between snow study approaches need to be accounted for when projecting snow dynamics and their impact on ecosystems in future climates.

Published
2022

Catalog

Books, media, physical & digital resources
See catalog results