检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Big Data and Smart Computing, BigComp 2025

作者： Hwang, Sooyeon Gweon, Gahgene Kwon, Eunseong Seoul National University Interdisciplinary Program in Artificial Intelligence Korea Republic of Seoul National University Graduate School of Convergence Science and Technology Korea Republic of POSTECH Dept. of Computer Science and Engineering Korea Republic of

Multimodal Emotion Recognition in Conversation (ERC) is a task of predicting the emotion of each utterance in a conversation by utilizing both verbal and non-verbal modalities. However, existing approaches often struggle to bridge cross-modal gaps, resulting in misaligned features and frequent misclassification of minority emotions into semantically similar majority emotions. To address these challenges, we propose MERNet, a framework that employs cross-modal knowledge distillation and contrastive learning to align multimodal features and effectively distinguish subtle emotions in conversations. Our framework consists of two stages: 1) guiding non-verbal modalities with the text modality to transfer knowledge and align their features, and 2) applying contrastive learning with emotion labels as anchors to distinguish subtle differences between similar emotions and address the class imbalance problem. Experiments conducted on two benchmark datasets, IEMOCAP and MELD, demonstrate that our MERNet outperforms existing state-of-the-art models. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Smart Data Augmentation for Multiclass Brain Tumor Detection with Imbalanced Data

Smart Data Augmentation for Multiclass Brain Tumor Detection...

引用

International Conference on Information Technology, Information Systems and electrical engineering (ICITISEE)

作者： Rizal Dwi Prayogo Hidetaka Nambo Division of Electrical Engineering and Computer Science Graduate School of Natural Science and Technology Kanazawa University Kanazawa Japan Faculty of Transdisciplinary Sciences Institute of Philosophy in Interdisciplinary Sciences Kanazawa University Kanazawa Japan

ISBN: (数字)9798350368970

ISBN: (纸本)9798350368987

Dealing with class imbalance is a significant issue in classification tasks that often leads to lower prediction performance. Many data augmentation methods have been suggested to tackle this problem, but their effectiveness can vary depending on the dataset. Utilizing augmentation methods can improve the learning and generalization abilities of the proposed convolutional neural network (CNN) model. However, it is challenging to find a single data augmentation method that can effectively address class imbalance problems across all scenarios. In this paper, we present a technique known as smart data augmentation (SDA) that is aimed at effectively improving classification performance by enhancing imbalanced data. SDA involves an equation that can be used to create an augmentation technique, combining different sampling methods for addressing multiclass imbalance and offering easy customization options. We perform the data balancing strategy including undersampling, oversampling, and SDA-based sampling. We evaluate our proposed framework using a CNN model to improve the detection of brain tumors in imbalanced data. Our experiments demonstrate that SDA-based sampling improves brain tumor detection performance by 3.546% in accuracy, 3.310% in precision, 3.432% in recall, and 3.371 % in Fl-score compared to the imbalanced data scenario. The findings suggest that utilizing SDA together with CNN can improve the classification performance of brain tumor detection with imbalanced data.

关键词： electrical engineering Data augmentation Sampling methods Brain modeling Mathematical models Data models Convolutional neural networks Information technology Biological neural networks Information systems

来源：评论

学校读者我要写书评

暂无评论

Understanding the stability of advanced inorganic-organic hybrid thin films for advanced resist applications 41

Understanding the stability of advanced inorganic-organic hy...

引用

Advances in Patterning Materials and Processes XLI 2024

作者： Le, Dan N. Chu, Thi Thu Huong Kim, Jin-Hyun Veyan, Jean-Francois Lee, Won-Il Tiwale, Nikhil Lee, Minjong Choi, Seungsoo Woo, Jihoon Nam, Chang-Yong Choi, Rino Kim, Jiyoung Department of Materials Science and Engineering University of Texas at Dallas RichardsonTX75080 United States Department of Materials Science and Chemical Engineering Stony Brook University Stony BrookNY11794 United States Center for Functional Nanomaterials Brookhaven National Laboratory UptonNY11973 United States Department of Electrical and Computer Engineering University of Texas at Dallas RichardsonTX75080 United States Program in Enviromental and Polymer Engineering Inha University Incheon22212 Korea Republic of Department of Materials Science and Engineering Inha University Incheon22212 Korea Republic of

ISBN: (纸本)9781510672208

In this study, we focus on examining the stability of Al-based inorganic-organic hybrid thin films deposited through the molecular atomic layer deposition (MALD) process in ambient environment. Our observations reveal an initial reduction in material thickness within the first 3 days, followed by a period of stability. XPS analysis is employed to further investigate the chemical alternations in the aged Al-based hybrid thin films, revealing an increase in C=O species as well as overall oxygen content in the material. We also evaluate the effects of atmospheric exposure on the sensitivity of the Al-based hybrid thin films using electron flood exposure. This study aims to enhance the understanding of the stability of a vapor-phase synthesized hybrid thin film system for advanced resist applications. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Atomic layer deposition

来源：评论

学校读者我要写书评

暂无评论

FDAM: Filter-Dedicated Approximate Multiplier Design for Real-Time CNN Acceleration

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Nguyen, Kihwan Kim Xuan Truong Jeon, Dongsuk Lee, Hyuk-Jae Korea Republic of program Department of Electrical Engineering Seoul08826 Korea Republic of Inter-University Semiconductor Research Center Seoul National University Graduate School of Convergence Science and Technology Research Institute for Convergence Science Seoul08826 Korea Republic of Department of Electrical and Computer Engineering Seoul08826 Korea Republic of

Video super-resolution (VSR) is widely used in various high-definition applications, such as HDTVs and smartphones, requiring a dedicated upscaling technique for realtime full-HD generation. To reduce on-chip buffers for largesize output feature maps, a streaming VSR accelerator may employ an output stationary dataflow, leading to a large energy consumption caused by frequent filter switching. To mitigate this, we introduce a new filter-dedicated multiplier design for realtime VSR acceleration. We replace costly multipliers with adders, shifters, and multiplexers (MUXes), referred to as unified multiple constant multiplications (UMCM). The conventional UMCM, however, may incur considerable area/power overhead due to the unified topology constraint among different filter sets. To address this problem, we propose a new approximated MCM (AMCM) problem to relax the constraint and an approximate compatible graph synthesis (A-CGS) framework to efficiently solve AMCM by jointly searching for approximated filters and constructing a unified graph. Additionally, we suggest a lightweight finetuning method by freezing approximated filters and only finetuning biases, which can recover the original model’s accuracy within a few epochs. Experimental results with synthetic data demonstrate that AMCM reduces the area by up to 49.8%, 44.8%, and 40.3% when considering constant sets of 2, 4, and 8, respectively. Our designs with SR application achieve up to a 73.3% reduction in energy consumption. Experiments with the Set5 and Set14 datasets show that our model with bias correction achieves similar restoration performance compared to the eightbit models. © 1982-2012 IEEE.

关键词： Acceleration

来源：评论

学校读者我要写书评

暂无评论

ControlDreamer: Blending Geometry and Style in Text-to-3D

arXiv

引用

arXiv 2023年

作者： Oh, Yeongtak Choi, Jooyoung Kim, Yongsung Park, Minjun Shin, Chaehun Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Republic of

Recent advancements in text-to-3D generation have significantly contributed to the automation and democratization of 3D content creation. Building upon these developments, we aim to address the limitations of current methods in blending geometries and styles in text-to-3D generation. We introduce multi-view ControlNet, a novel depth-aware multi-view diffusion model trained on generated datasets from a carefully curated text corpus. Our multi-view ControlNet is then integrated into our two-stage pipeline, ControlDreamer, enabling text-guided generation of stylized 3D models. Additionally, we present a comprehensive benchmark for 3D style editing, encompassing a broad range of subjects, including objects, animals, and characters, to further facilitate research on diverse 3D generation. Our comparative analysis reveals that this new pipeline outperforms existing text-to-3D methods as evidenced by human evaluations and CLIP score metrics. Project page: https://***. © 2023, CC BY.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Tuning Zinc-Copper Dual-Ion Electrolytes to Extend the Cycle Life of Zinc Ion Capacitors

Tuning Zinc-Copper Dual-Ion Electrolytes to Extend the Cycle...

引用

International Flexible Electronics Technology Conference (IFETC)

作者： Jinwook Jung Chanho Shin Tse Nga Ng Program in Materials Science and Engineering University of California San Diego La Jolla USA Department of Electrical and Computer Engineering University of California San Diego La Jolla USA

ISBN: (数字)9798331529468

ISBN: (纸本)9798331529475

We investigated the effect of copper ion concentration in zinc-copper dual-ion electrolytes to suppress dendrites and extend the cycle life of zinc ion capacitors. The devices were characterized in terms of changes in microstructure and cycling stability. The nuclei size was decreased in the optimal copper ion concentration to promote lateral deposition and avoid vertical dendrites. The device exhibited stable cycling performance with a capacitance retention of 95% after 10,000 redox cycles, compared to the device with single zinc ion electrolyte which short circuited at around 1,250 redox cycles.

关键词： Performance evaluation Capacitors Redox Ions Electrolytes Dendrites (neurons) Copper Microstructure Zinc Tuning

来源：评论

学校读者我要写书评

暂无评论

Battling the Non-stationarity in Time Series Forecasting via Test-time Adaptation 39

Battling the Non-stationarity in Time Series Forecasting via...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Kim, HyunGi Kim, Siwon Mok, Jisoo Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of AIIS ASRI INMC Seoul National University Korea Republic of

ISBN: (纸本)157735897X

Deep Neural Networks have spearheaded remarkable advancements in time series forecasting (TSF), one of the major tasks in time series modeling. Nonetheless, the non-stationarity of time series undermines the reliability of pre-trained source time series forecasters in mission-critical deployment settings. In this study, we introduce a pioneering test-time adaptation framework tailored for TSF (TSF-TTA). TAFAS, the proposed approach to TSF-TTA, flexibly adapts source forecasters to continuously shifting test distributions while preserving the core semantic information learned during pre-training. The novel utilization of partially-observed ground truth and gated calibration module enables proactive, robust, and model-agnostic adaptation of source forecasters. Experiments on diverse benchmark datasets and cutting-edge architectures demonstrate the efficacy and generality of TAFAS, especially in long-term forecasting scenarios that suffer from significant distribution shifts. Copyright © 2025, Association for the Advancement of Artificial Intelligence.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Harnessing Machine Learning for Increased Efficiency in Real-Time Data Analysis 3

Harnessing Machine Learning for Increased Efficiency in Real...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Singh, Dhiraj Kumar Umamaheswari, B. Junnarkar, Aparna A. Singh, Vaishali Singh, Manpreet Savitha, R. Vivekananda Global University Department of Electrical Engineering Jaipur India Prince Shri Venkateshwara Padmavathy Engineering College Department of Computer Science and Engineering Chennai127 India Vishwakarma Institute of Information Technology Department of Information Technology Pune India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Chitkara University Institute of Engineering and Technology Chitkara University Centre of Interdisciplinary Research in Business and Technology Punjab India Electrical and Electronics Engineering Faculty of Engineering and Technology Kanataka Bangalore India

ISBN: (纸本)9798350319125

The goal of this research is to analyze the ability of device mastering (ML) to increase the efficiency of real-time records evaluation. Notably, the focus is on leveraging ML techniques to correctly pick out, examine, and categorize information streams as a way to offer more green selection-making possibilities. This study will explore present ML strategies, which include supervised and unsupervised learning, deep studying, and reinforcement learning, and their software for real-time statistics evaluation. Additionally, the studies will remember the feasibility of combining ML strategies with present information science strategies and technology, including streaming data infrastructure and facts engineering. Sooner or later, the research will compare the potential prices and benefits of enforcing the sort of device in phrases of computational requirements, statistics handling, and accuracy. Via presenting insight into the feasibility of device mastering for actual-time records analysis, this research aims to cope with the issue of scalability in present-day techniques and help tell future selections in statistics engineering and analytics. © 2023 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Battling the Non-stationarity in Time Series Forecasting via Test-time Adaptation

arXiv

引用

arXiv 2025年

Deep Neural Networks have spearheaded remarkable advancements in time series forecasting (TSF), one of the major tasks in time series modeling. Nonetheless, the non-stationarity of time series undermines the reliability of pre-trained source time series forecasters in mission-critical deployment settings. In this study, we introduce a pioneering test-time adaptation framework tailored for TSF (TSF-TTA). TAFAS, the proposed approach to TSF-TTA, flexibly adapts source forecasters to continuously shifting test distributions while preserving the core semantic information learned during pre-training. The novel utilization of partially-observed ground truth and gated calibration module enables proactive, robust, and model-agnostic adaptation of source forecasters. Experiments on diverse benchmark datasets and cutting-edge architectures demonstrate the efficacy and generality of TAFAS, especially in long-term forecasting scenarios that suffer from significant distribution shifts. The code is available at https://***/kimanki/TAFAS. © 2025, CC BY-NC-SA.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Concept Bottleneck Models

arXiv

引用

arXiv 2023年

作者： Kim, Eunji Jung, Dahuin Park, Sangha Kim, Siwon Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Republic of

Interpretable models are designed to make decisions in a human-interpretable manner. Representatively, Concept Bottleneck Models (CBM) follow a two-step process of concept prediction and class prediction based on the predicted concepts. CBM provides explanations with high-level concepts derived from concept predictions;thus, reliable concept predictions are important for trustworthiness. In this study, we address the ambiguity issue that can harm reliability. While the existence of a concept can often be ambiguous in the data, CBM predicts concepts deterministically without considering this ambiguity. To provide a reliable interpretation against this ambiguity, we propose Probabilistic Concept Bottleneck Models (ProbCBM). By leveraging probabilistic concept embeddings, ProbCBM models uncertainty in concept prediction and provides explanations based on the concept and its corresponding uncertainty. This uncertainty enhances the reliability of the explanations. Furthermore, as class uncertainty is derived from concept uncertainty in ProbCBM, we can explain class uncertainty by means of concept uncertainty. Code is publicly available at https://***/ejkim47/prob-cbm. © 2023, CC BY-NC-SA.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：