检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Jo, Sanghyun Lee, Ziseok Lee, Wooyeol Kim, Kyungsu OGQ Seoul Korea Republic of Department of Biomedical Sciences Seoul National University Seoul Korea Republic of Department of Computer Science and Engineering Seoul National University Seoul Korea Republic of School of Transdisciplinary Innovations Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Republic of

Achieving precise panoptic segmentation heavily relies on pixel-wise instance annotations, but obtaining such datasets is costly. Unsupervised instance segmentation (UIS) eliminates annotation requirements but struggles with adjacent instance merging and single-instance fragmentation, largely due to the limitations of DINO-based backbones, which lack strong instance separation cues. Weakly-supervised panoptic segmentation (WPS) reduces annotation costs by using sparse labels (e.g., points, boxes), yet these annotations remain expensive and introduce human bias and boundary errors, limiting performance. To address these challenges, we propose DiffEGG (Diffusion-Driven EdGe Generation), a fully annotation-free method that extracts instance-aware features from pretrained diffusion models to generate precise instance edge maps. DiffEGG fundamentally differs from prior UIS and WPS approaches by leveraging pretrained diffusion models as a backbone. Unlike DINO-based UIS methods, diffusion models inherently capture fine-grained, instance-aware features, enabling more precise boundary delineation. DiffEGG further enhances edge connectivity through self-supervised fine-tuning, progressively improving instance separation. For WPS, DiffEGG completely eliminates annotation costs and human bias by operating without any form of manual supervision, addressing the key limitations of prior best methods. Additionally, we introduce RIP, a post-processing technique that fuses DiffEGG’s edge maps with segmentation masks in a task-agnostic manner. This broad applicability allows DiffEGG to be seamlessly integrated into various segmentation frameworks. When applied to UIS, DiffEGG and RIP achieve an average +4.4 AP improvement over prior best UIS methods. When combined with weakly-supervised semantic segmentation (WSS), DiffEGG enables WPS without instance annotations, outperforming prior best point-supervised WPS methods by +1.7 PQ. These results demonstrate that DiffEGG’s edge maps serv

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Characteristics Fluctuation of Sub-3-nm Bulk FinFET Devices Induced by Random Interface Traps

Characteristics Fluctuation of Sub-3-nm Bulk FinFET Devices ...

引用

IEEE Conference on Nanotechnology

作者： Sekhar Reddy Kola Min-Hui Chuang Yiming Li Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program National Yang Ming Chiao Tung University Hsinchu Taiwan Department of Electronics and Electrical Engineering Institute of Communications Engineering Institute of Biomedical Engineering Institute of Pioneer Semiconductor Innovation Institute of Artificial Intelligence Innovation National Yang Ming Chiao Tung University Hsinchu Taiwan

Three-dimensional (3D) bulk fin-typed field effect transistors (FinFETs) have emerged as key devices that can scale down the technology node beyond 22-nm. However, the scaled devices have created new sources of fluctuation inherent in 3D geometry. The interface trap is one such fluctuation that is caused by the trapping and de-trapping of charge carriers and has an adverse effect on device characteristics and variability. In this work, we study impacts of random interface traps (RITs) on electrical characteristic of bulk FinFETs by using a 3D quantum-mechanically corrected device simulation. RIT position effects on short channel effects (SCEs) are examined with physical governed influence to show the major fluctuations. More than 50% reductions of the RITs-induced characteristic fluctuation of the germanium (Ge) devices are observed, compared with Si devices. The Ge ones can reduce SCE variations and exhibit high immunity to RITs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mass Spectra Prediction with Structural Motif-based Graph Neural Networks

arXiv

引用

arXiv 2023年

作者： Park, Jiwon Jo, Jeonghee Yoon, Sungroh Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul08826 Korea Republic of LG Chem Seoul07795 Korea Republic of Seoul02456 Korea Republic of Department of Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of Artificial Intelligence Institute Seoul National University Seoul08826 Korea Republic of

Mass spectra, which are agglomerations of ionized fragments from targeted molecules, play a crucial role across various fields for the identification of molecular structures. A prevalent analysis method involves spectral library searches, where unknown spectra are cross-referenced with a database. The effectiveness of such search-based approaches, however, is restricted by the scope of the existing mass spectra database, underscoring the need to expand the database via mass spectra prediction. In this research, we propose the Motif-based Mass Spectrum Prediction Network (MoMS-Net), a system that predicts mass spectra using the information derived from structural motifs and the implementation of Graph Neural Networks (GNNs). We have tested our model across diverse mass spectra and have observed its superiority over other existing models. MoMS-Net considers substructure at the graph level, which facilitates the incorporation of long-range dependencies while using less memory compared to the graph transformer model. © 2023, CC BY.

关键词： Molecules

来源：评论

学校读者我要写书评

暂无评论

A Detailed Analysis of Qualitative and Quantitative Factors in Realization of 6G Communication

A Detailed Analysis of Qualitative and Quantitative Factors ...

引用

International Conference on Internet of Things: Systems, Management and Security

作者： Mohammad Alja’Afreh Ali Karime Sahel Alouneh Abdulmotaleb El Saddik Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI) UAE School of Electrical Engineering and Computer Science University of Ottawa Canada Department of Electrical and Computer Engineering The Royal Military College of Canada Canada Cybersecurity Program College of Engineering AL AIN University UAE Computer Engineering Department German Jordanian University

Undoubtedly, the world has so far faced a pandemic which is reshaping daily lives and business activities. Even at current endemic stages, special focus on maintaining physical distancing norms for curbing the expeditious spread of the disease, many institutions, individuals and industries rely on communications networks or telecoms for ensuring service consistency to avoid complete termination of their business operations and other activities. This has put enormous pressure on mobile networks and communication systems thereby making the technology experts to think more about introducing rapid speed, vast coverage and high connectivity networks. The extensive application of fresh communication networks and enabling technologies have impelled the advent of 6G communication networks. As 6G is still in its inception phase, its complete realization requires a proper and high understanding of diverse quantitative and qualitative factors supporting its deployment. From this standpoint, this survey article intends to deeply explore 6G networks, their significance and prerequisites. This paper provides a succinct theoretical background of 6G technology, and reviews the diverse enabling technologies and existing works undertaken on core technologies. It explores the prevailing gaps in research for providing readers to gain information regarding challenges in perfect 6G network realization and implementation thus paving the road for a successful 6G vision.

关键词： 6G mobile communication Systematics Pandemics Roads Telecommunications Communication networks Security

来源：评论

学校读者我要写书评

暂无评论

ECG signals-based security and steganography approaches in WBANs: A comprehensive survey and taxonomy

引用

Sustainable Computing: Informatics and Systems 2024年 41卷

作者： Masdari, Mohammad Band, Shahab S. Qasem, Sultan Noman Sayed, Biju Theruvil Pai, Hao-Ting Department of Computer Engineering Urmia Branch Islamic Azad University Urmia Iran Future Technology Research Center National Yunlin University of Science and Technology Douliu Taiwan Department of Information Management International Graduate School of Artificial Intelligence National Yunlin University of Science and Technology Taiwan Riyadh11432 Saudi Arabia Computer Science Department Faculty of Applied Science Taiz University Taiz6803 Yemen Department of Computer Science Dhofar University PO Box 2509 SalalahPCode 211 Oman Bachelor Program of Big Data Applications in Business National Pingtung University Pingtung Taiwan

Wireless Body Area Networks (WBANs) are integral components of e-healthcare systems, responsible for monitoring patients' physiological states through intelligent implantable or wearable sensor nodes. These nodes collect medical data, which is then transmitted to remote healthcare facilities for thorough evaluation. Securing medical data within WBANs is paramount due to its central role in preserving patient privacy and confidentiality. Notably, Electrocardiogram (ECG) signals have recently gained prominence as pivotal elements within diverse security frameworks. Incorporating ECG signals strategically enhances the security and reliability of WBANs and broader e-healthcare systems, instilling greater trustworthiness. This survey article provides an in-depth exploration of contemporary ECG-based security schemes, adding to the scholarly discourse. The imperative to categorize these security paradigms revolves around their use of ECG signals. This categorization identifies three key domains: the first involves schemes that utilize ECG signals for cryptographic operations, encompassing key generation, agreement, management, and authentication. The second category employs steganography-based techniques, using ECG signals to conceal patients' sensitive medical data. The third category focuses on enhancing ECG signal security during data transmission. Each category is meticulously elaborated, detailing architectural foundations, notable contributions, and intrinsic security services. Furthermore, each section presents a comprehensive overview of the attributes characterizing ECG-based security frameworks. This includes insights into employed datasets, simulation environments, evaluation metrics, and inherent advantages and limitations. Expanding on this, a thorough analysis of distinctive attributes underpinning these security frameworks concludes by shedding light on potential directions for future research. © 2023 Elsevier Inc.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

EXOT: Exit-aware Object Tracker for Safe Robotic Manipulation of Moving Object

arXiv

引用

arXiv 2023年

作者： Kim, Hyunseo Yoon, Hye Jung Kim, Minji Han, Dong-Sig Zhang, Byoung-Tak Interdisciplinary Program in Neuroscience Seoul National University Seoul Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of Dept. of Computer Science and Engineering Seoul National University Korea Republic of AIIS Seoul National University Korea Republic of

Current robotic hand manipulation narrowly operates with objects in predictable positions in limited environments. Thus, when the location of the target object deviates severely from the expected location, a robot sometimes responds in an unexpected way, especially when it operates with a human. For safe robot operation, we propose the EXit-aware Object Tracker (EXOT) on a robot hand camera that recognizes an object's absence during manipulation. The robot decides whether to proceed by examining the tracker's bounding box output containing the target object. We adopt an out-of-distribution classifier for more accurate object recognition since trackers can mistrack a background as a target object. To the best of our knowledge, our method is the first approach of applying an out-of-distribution classification technique to a tracker output. We evaluate our method on the first-person video benchmark dataset, TREK-150, and on the custom dataset, RMOT-223, that we collect from the UR5e robot. Then we test our tracker on the UR5e robot in real-time with a conveyor-belt sushi task, to examine the tracker's ability to track target dishes and to determine the exit status. Our tracker shows 38% higher exit-aware performance than a baseline method. The dataset and the code will be released at https://***/hskAlena/EXOT. Copyright © 2023, The Authors. All rights reserved.

关键词： Belt conveyors

来源：评论

学校读者我要写书评

暂无评论

Boosting the Performance of Image Restration Models Through Training with Deep-Feature Auxiliary Guidance

SSRN

引用

SSRN 2024年

作者： Jang, Cheolhun Ji, Deahyun Cho, Nam Ik Interdisciplinary Program in Artificial Intelligence INMC Seoul National University Seoul08826 Korea Republic of Samsung Advanced Institute of Technology Suwon-si Gyenggi-do16678 Korea Republic of Department of Electrical and Computer Engineering INMC Seoul National University Seoul08826 Korea Republic of

Many neural network architectures have been suggested for image restoration models to enhance the accuracy of restored images while keeping the computational time reasonable. However, most previous studies have primarily focused on introducing new network architectures, with relatively less emphasis on efficient training techniques. This paper introduces a novel training strategy that improves the accuracy of image restoration models without increasing inference times by preserving their structures. To achieve this, we add auxiliary guidance at a feature map of each multi-scale level during the training process. All modules added to the model for the application of auxiliary guidance are only used during training time and can be removed at the inference phase, thereby eliminating the need for additional computation. Our proposed training method, named deep-feature auxiliary guidance (DFAG), can be easily applied to existing encoder-decoder architectures. By applying DFAG to train existing image restoration models, we have obtained enhanced performance in real-image denoising, Gaussian denoising, motion deblurring, JPEG artifact reduction, and super-resolution for all tested models. The source code and pre-train models will be released. © 2024, The Authors. All rights reserved.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

MathSpeech: Leveraging Small LMs for Accurate Conversion in Mathematical Speech-to-Formula

arXiv

引用

arXiv 2024年

作者： Hyeon, Sieun Jung, Kyudan Won, Jaehee Kim, Nam-Joon Ryu, Hyun Gon Lee, Hyuk-Jae Do, Jaeyoung Department of Electrical and Computer Engineering Seoul National University Korea Republic of Department of Mathematics Chung-Ang University Korea Republic of College of Liberal Studies Seoul National University Korea Republic of NVIDIA United States Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

In various academic and professional settings, such as mathematics lectures or research presentations, it is often necessary to convey mathematical expressions orally. However, reading mathematical expressions aloud without accompanying visuals can significantly hinder comprehension, especially for those who are hearing-impaired or rely on subtitles due to language barriers. For instance, when a presenter reads Euler’s Formula, current Automatic Speech Recognition (ASR) models often produce a verbose and error-prone textual description (e.g., e to the power of i x equals cosine of x plus i side of x), instead of the concise LATEX format (i.e., eix = cos(x) + isin(x)), which hampers clear understanding and communication. To address this issue, we introduce MathSpeech, a novel pipeline that integrates ASR models with small Language Models (sLMs) to correct errors in mathematical expressions and accurately convert spoken expressions into structured LATEX representations. Evaluated on a new dataset derived from lecture recordings, MathSpeech demonstrates LATEX generation capabilities comparable to leading commercial Large Language Models (LLMs), while leveraging fine-tuned small language models of only 120M parameters. Specifically, in terms of CER, BLEU, and ROUGE scores for LATEX translation, MathSpeech demonstrated significantly superior capabilities compared to GPT-4o. We observed a decrease in CER from 0.390 to 0.298, and higher ROUGE/BLEU scores compared to GPT-4o. Copyright © 2024, The Authors. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Dynamic Numerical Studies of a Rotorcraft Entering and Exiting Rectangular Tunnel

Dynamic Numerical Studies of a Rotorcraft Entering and Exiti...

引用

IEEE International Conference on e-Business engineering (ICEBE)

作者： Uzu-Kuei Hsu Hong-Bin Chang Yao-Yu Tsai Chang-Hsien Tai Bachelor Program in Artificial Intelligence and Mechatronics National Pingtung University of Science and Technology Kaohsiung City Taiwan SCERDC General Research Service Center National Pingtung University of Science and Technology Kaohsiung City Taiwan Dept. of Vehicle Engineering National Pingtung University of Science and Technology Kaohsiung City Taiwan ROC

In recent years, the utilization of multi-rotor drones has seen a steady rise. Unmanned aerial vehicles (UAV) have found diverse applications, including aerial photography, transportation, military operations, and agriculture. The advent of these compact flying machines offers humanity a range of convenient and versatile choices across various sectors. Although unmanned aerial vehicles hold significant practical value, their stable flight is contingent on favorable weather conditions. Consequently, it becomes crucial to investigate the influence of environmental airflow on aircraft stability. This is particularly important for small machines like rotary-wing aircraft operating in confined spaces, where understanding the aerodynamic effects of the flow field is crucial to avert potential crashes. This study delves into the variations in the flow field during the entry and exit of a single rotor into a tunnel. Utilizing dynamic simulations, it examines how tunnels impact the rotor’s flow field and analyzes thrust curves to understand dynamic rotor behavior. The study also explores the effect of vortex generation on the rotor and employs a simple square tunnel to assess how tunnel size and flight speed influence the rotor’s flow field during flight. The findings hold potential as reference points to enhance flight stability during tunnel flights.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Respiratory Disease Classification by CNN using MFCC

Respiratory Disease Classification by CNN using MFCC

引用

International Conference on Computing, Communication & Automation (ICCCA)

作者： Krishna Mridha Shakil Sarkar Dinesh Kumar Computer Engineering Marwadi University Rajkot Gujarat India Bachelor of Pharmacy Marwadi University Rajkot Gujarat India Computer Engineering Artificial Intelligence & Big Data Marwadi University Rajkot India

ISBN: (纸本)9781665447539

Respiratory disease is a sort of sickness that produces a high death rate in rural or urban settings. Respiratory illnesses must be detected in advance and the rapid growth of deep learning over the last several years will lead the analysis and calculation of respiratory sound by computer computing power into a new trend of disease detection. Noting recent progress in the field of image classification, in which CNN's are utilized to categories high-precision pictures. A technique of classification of breathing sonority by CNN is proposed in this work, where it is trained. To this end, each audio sample was visually represented, enabling the identification of classification resources by applying the same methodologies to categories of high-precision pictures. We employed the Mel frequency cepstral coefficients method (MFCCs). We extracted resources with MFCC for every audio file in the dataset, meaning for every audio sample that we have an image representation. In the categorization of respiratory diseases utilized in the six classes accessible in the database, the approach described in this article achieved results over 93 percent. The six classifications are COPD (Chronic Pulmonary Obstructive Disease), Healthy, URTI (Upper Respiratory Tract Infection), Bronchiectasis, Pneumonia, Bronchiolitis.

关键词： Deep learning Databases Pulmonary diseases Conferences Lung Lead Image representation

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：