检索结果-内蒙古大学图书馆

IEEE EMBS International Conference on Information Technology Applications in Biomedicine (ITAB)

作者： Shun-Cheng Chang Hsin-Pei Yu Yi-Hsien Hsieh Pochuang Wang Weichung Wang Tung-Hung Su Jia-Horng Kao Che Lin Graduate Institute of Communication Engineering National Taiwan University (NTU) Taipei Taiwan Department of Computer Science and Information Engineering NTU Taipei Taiwan Institute of Applied Mathematical Sciences NTU Taipei Taiwan Department of Internal Medicine Division of Gastroenterology and Hepatology National Taiwan University Hospital Taipei Taiwan Department of Electrical Engineering NTU Taipei Taiwan Center for Advanced Computing and Imaging in Biomedicine NTU Taipei Taiwan Smart Medicine and Health Informatics Program NTU Taipei Taiwan

ISBN: (数字)9798350351552

ISBN: (纸本)9798350351569

Deep learning has revolutionized medical imaging, offering advanced methods for accurate diagnosis and treatment planning. The BCLC staging system is crucial for staging Hepatocellular Carcinoma (HCC), a high-mortality cancer. An automated BCLC staging system could significantly enhance diagnosis and treatment planning efficiency. However, we found that BCLC staging, which is directly related to the size and number of liver tumors, aligns well with the principles of the Multiple Instance Learning (MIL) framework. To effectively achieve this, we proposed a new preprocessing technique called Masked Cropping and Padding(MCP), which addresses the variability in liver volumes and ensures consistent input sizes. This technique preserves the structural integrity of the liver, facilitating more effective learning. Furthermore, we introduced Re ViT, a novel hybrid model that integrates the local feature extraction capabilities of Convolutional Neural Networks (CNNs) with the global context modeling of Vision Transformers (ViTs). Re ViT leverages the strengths of both architectures within the MIL framework, enabling a robust and accurate approach for BCLC staging. We will further explore the trade-off between performance and interpretability by employing TopK Pooling strategies, as our model focuses on the most informative instances within each bag.

关键词： Visualization Accuracy Three-dimensional displays Liver Transformers Planning Convolutional neural networks Context modeling Biomedical imaging Tumors

来源：评论

学校读者我要写书评

暂无评论

Enhancing Diagnostic Accuracy for Knee Osteoarthritis Using a Deep Learning Approach

Enhancing Diagnostic Accuracy for Knee Osteoarthritis Using ...

引用

International Symposium on Applied science 2024, ISAS 2024

作者： Raza, Aquib Ching, Congo Tak Shing Liu, Peng-Ta Phan, Thien-Luan Tran, Ngoc-Luan Nguyen, Ha Anh T. Rameez, Mohammad Li, Hung-Chung Linh, Dao Nguyen Phuong Van Hieu, Nguyen Tran, Trung Nghia National Taiwan University Taipei City10673 Taiwan Research Center for Information Technology Academia Sinica Taipei City11529 Taiwan Graduate Institute of Biomedical Engineering National Chung Hsing University Taichung402 Taiwan Department of Electrical Engineering National Chi Nan University Nantou County Taiwan Advanced Plant and Food Crop Biotechnology Center National Chung Hsing University Taichung402 Taiwan International Doctoral Program in Agriculture National Chung Hsing University Taichung402 Taiwan Fall Prevention Center Department of Physical Medicine & Rehabilitation Changhua Christian Hospital Changhua500 Taiwan Department of Physics and Electronic Engineering University of Science Vietnam National University - Ho Chi Minh City Ho Chi Minh City70000 Viet Nam Department of Computer Science University of York York HeslingtonYO10 5DD United Kingdom Undergraduate Program of Intellectual Creativity Engineering National Chung Hsing University Taichung402 Taiwan Ho Chi Minh City72409 Viet Nam HCMUT Vietnam National University Ho Chi Minh City Thu Duc Ho Chi Minh City71308 Viet Nam

This research introduces a deep learning framework that combines convolutional neural networks with autoencoders to improve the diagnostic accuracy of knee osteoarthritis. The study utilized a publicly available dataset from the Mendeley Data repository, where knee joint images were preprocessed using Contrast Limited Adaptive Histogram Equalization to enhance contrast and ensure consistent image sizing. Initially, an autoencoder was employed in an unsupervised manner to learn compressed representations of the data. These representations were then used to train a CNN to classify knee images into 'healthy' and 'osteoarthritic' categories. The model was trained using an 80:20 split for training and testing data, incorporating early stopping and data augmentation techniques to prevent overfitting and enhance generalization. Performance metrics such as accuracy, precision, recall, and the area under the Receiver Operating Characteristic curve (ROCAUC) were used to evaluate the model, resulting in a high test accuracy of 98.95%. The high precision and recall rates further confirmed the model's robustness in diagnosing KOA. To enhance interpretability, Gradient-weighted Class Activation Mapping (Grad-CAM) was applied to identify critical regions in the images that influenced the model's decisions. Additionally, t-Distributed Stochastic Neighbor Embedding (t-SNE) was used to visualize the high-dimensional encoded features in a two-dimensional space, providing deeper insights into how the model differentiates between classes. The promising results of this deep learning approach suggest its potential for broader applications in medical imaging diagnostics. By providing healthcare professionals with a tool that enhances diagnostic accuracy and operational efficiency, this framework lays the foundation for developing scalable, AI-driven diagnostic systems for various complex medical conditions. © 2025 Institute of Physics Publishing. All rights reserved.

关键词： Joints (anatomy)

来源：评论

学校读者我要写书评

暂无评论

Survival analysis of Kasturi tobacco plants in Jember district using the stratified cox and extended cox models.

引用

MethodsX 2025年 14卷

作者： Angga Iryanto Pratama Dwi Rantini Ratih Ardiati Ningrum Arip Ramadan Fazidah Othman Data Science Technology Study Program Faculty of Advanced Technology and Multidiscipline Universitas Airlangga Surabaya 60115 Indonesia Research Group of Data-Driven Decision Support System Faculty of Advanced Technology and Multidiscipline Universitas Airlangga Surabaya 60115 Indonesia Information System Study Program School of Industrial and System Engineering Telkom University Surabaya Campus Surabaya 60231 Indonesia Department of Computer System and Technology Faculty of Computer Science and Information Technology University of Malaya Malaya Malaysia

In 2022, tobacco was the top export commodity, generating $106.3 million in sales. East Java Province contributes significantly to Indonesia's tobacco production, with an annual output of 188.6 thousand tons. Jember Regency is the area in East Java Province which is a Kasturi tobacco cultivation area. The productivity of Kasturi tobacco continues to decrease due to several factors that can affect the survival of the tobacco. This study aims to analyze the survival of Kasturi tobacco by creating stratified Cox and extended Cox models in order to handle factors that cannot fulfill the proportional hazard assumption. Based on the results of the analysis, the stratified Cox model is the best model with AIC and BIC values of 798.108 and 805.5748 respectively, while the extended Cox has AIC and BIC values of 840.2186 and 850.1732 respectively. Variables that can significantly affect the survival of Kasturi tobacco are the variable concentration of ZA fertilizer, pesticide concentration. The addition of ZA fertilizer must be appropriate, because if excessive it can cause poisoning of tobacco plants. Likewise with pesticides, if excessive it will cause damage to the leaves. This policy can increase the productivity of Kasturi tobacco. Then, Jember Regency contributes greater export capacity. • This paper aims to determine the factors that affect the survival of Kasturi tobacco plants in Jember • By using the extended Cox model, the best one is obtained using the Heaviside function with AIC and BIC values of 840.2186 and 850.1732, respectively • The stratified Cox model is better than the extended Cox model, which has AIC and BIC values of 798.108 and 805.5748, respectively

关键词： Productive agriculture Cox proportional hazard Stratified cox Extended cox Kasturi tobacco Cox Proportional Hazard Model, Stratified Cox Model, and Extended Cox Model

来源：评论

学校读者我要写书评

暂无评论

Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations

arXiv

引用

arXiv 2022年

作者： Jin, Peng Huang, Jinfa Liu, Fenglin Wu, Xian Ge, Shen Song, Guoli Clifton, David A. Chen, Jie School of Electronic and Computer Engineering Peking University China Peng Cheng Laboratory Shenzhen China -Preferred Program Peking University Shenzhen Graduate School China Department of Engineering Science University of Oxford United Kingdom Tencent JARVIS Lab China Oxford-Suzhou Centre for Advanced Research Suzhou China

Most video-and-language representation learning approaches employ contrastive learning, e.g., CLIP [53], to project the video and text features into a common latent space according to the semantic similarities of text-video pairs. However, such learned shared latent spaces are not often optimal, and the modality gap between visual and textual representation can not be fully eliminated. In this paper, we propose Expectation-Maximization Contrastive Learning (EMCL) to learn compact video-and-language representations. Specifically, we use the Expectation-Maximization algorithm to find a compact set of bases for the latent space, where the features could be concisely represented as the linear combinations of these bases. Such feature decomposition of video-and-language representations reduces the rank of the latent space, resulting in increased representing power for the semantics. Extensive experiments on three benchmark text-video retrieval datasets prove that our EMCL can learn more discriminative video-and-language representations than previous methods, and significantly outperform previous state-of-the-art methods across all metrics. More encouragingly, the proposed method can be applied to boost the performance of existing approaches either as a jointly training layer or an out-of-the-box inference module with no extra training, making it easy to be incorporated into any existing methods‡ Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Modelling the Human Immune System Response to the ChAdOx1 nCoV-19 Vaccine

Modelling the Human Immune System Response to the ChAdOx1 nC...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Xavier, Maicom Peters Pompei, Lara T. De O. Vieira, Ana Carolina G. De Paula, Matheus A. M. Bonin, Carla R. B. Reis, Ruy F. Pigozzo, Alexandre B. Quintela, Barbara De M. Dos Santos, Rodrigo W. Lobosco, Marcelo Federal University of Juiz de Fora Graduate Program on Computational Modeling Juiz de Fora Brazil Federal University of Juiz de Fora FISIOCOMP Juiz de Fora Brazil Federal University of Juiz de Fora GET-EngComp Juiz de Fora Brazil IF Sudeste MG Cataguases Advanced Campus Cataguases Brazil Federal University of Juiz de Fora Computer Science Department Juiz de Fora Brazil Federal University of São João Del-Rei Computer Science Department São João Del-Rei Brazil

ISBN: (纸本)9781665401265

About seven months after the start of the COVID-19 pandemic, the first vaccine against the disease was approved for emergency use. Since then, twenty-three more vaccines have been approved, while more than three hundred are in development. Despite being one of the fastest vaccines ever created, several questions about it remain open. Computational models can be useful to answer some of these questions. This paper aims to evaluate whether a computer model previously used to reproduce the effects of the yellow fever vaccine in the body is also capable of reproducing the effects of a distinct vaccine: ChAdOx1 nCoV-19. Preliminary results show that the model is a promising tool to achieve this goal since it was able to reproduce the antibody curves observed in individuals vaccinated with ChAdOx1 nCoV-19. © 2021 IEEE.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Ultrastrong Spin-Photon Coupling in Gadolinium Gallium Garnet

Ultrastrong Spin-Photon Coupling in Gadolinium Gallium Garne...

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Kritzell, T. Elijah Bao, Junzhe Doumani, Jacques Lee, Jae Joon Xu, Hongjing Tay, Fuyang Nojiri, Hiroyuki Bamba, Motoaki Baydin, Andrey Kono, Junichiro Department of Electrical and Computer Engineering Rice University HoustonTX77005 United States Applied Physics Graduate Program Smalley-Curl Institute Rice University HoustonTX77005 United States Department of Physics and Astronomy Rice University HoustonTX77005 United States Institute for Materials Research Tohoku University Sendai980-8577 Japan The Hakubi Center for Advanced Research Kyoto University Kyoto606-8502 Japan Department of Physics I Kyoto University Kyoto606-8502 Japan Smalley-Curl Institute Rice University HoustonTX77005 United States Department of Material Science and NanoEngineering Rice University HoustonTX77005 United States

We examine ultrastrong coupling of an ensemble of paramagnetic spins in Gd3Ga5O12 with terahertz photons in the presence of a high external magnetic field both in the bulk and thin-film limits. © 2023 The Author(s)

ISBN: (纸本)9781957171258

关键词： Photons

来源：评论

学校读者我要写书评

暂无评论

Position: Bayesian deep learning is needed in the age of large-scale AI 24

Position: Bayesian deep learning is needed in the age of lar...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Theodore Papamarkou Maria Skoularidou Konstantina Palla Laurence Aitchison Julyan Arbel David Dunson Maurizio Filippone Vincent Fortuin Philipp Hennig José Miguel Hernández-Lobato Aliaksandr Hubin Alexander Immer Theofanis Karaletsos Mohammad Emtiyaz Khan Agustinus Kristiadi Yingzhen Li Stephan Mandt Christopher Nemeth Michael A. Osborne Tim G. J. Rudner David Rügamer Yee Whye Teh Max Welling Andrew Gordon Wilson Ruqi Zhang Department of Mathematics The University of Manchester Manchester UK Eric and Wendy Schmidt Center Broad Institute of MIT and Harvard Cambridge Spotify London UK Computational Neuroscience Unit University of Bristol Bristol UK Centre Inria de l'Université Grenoble Alpes Grenoble France Department of Statistical Science Duke University Statistics Program KAUST Saudi Arabia Helmholtz AI Munich Germany and Department of Computer Science Technical University of Munich Munich Germany and Munich Center for Machine Learning Munich Germany Tübingen AI Center University of Tübingen Tübingen Germany Department of Engineering University of Cambridge Cambridge UK Department of Mathematics University of Oslo Oslo Norway and Bioinformatics and Applied Statistics Norwegian University of Life Sciences Ås Norway Department of Computer Science ETH Zurich Switzerland Chan Zuckerberg Initiative California Center for Advanced Intelligence Project RIKEN Tokyo Japan Vector Institute Toronto Canada Department of Computing Imperial College London London UK Department of Computer Science UC Irvine Irvine Department of Mathematics and Statistics Lancaster University Lancaster UK Department of Engineering Science University of Oxford Oxford UK Center for Data Science New York University New York Munich Center for Machine Learning Munich Germany and Department of Statistics LMU Munich Munich Germany DeepMind London UK and Department of Statistics University of Oxford Oxford UK Informatics Institute University of Amsterdam Amsterdam Netherlands Courant Institute of Mathematical Sciences and Center for Data Science Computer Science Department New York University New York Department of Computer Science Purdue University West Lafayette

In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets. However, a broader perspective reveals a multitude of overlooked metrics, tasks, and data types, such as uncertainty, active and continual learning, and scientific data, that demand attention. Bayesian deep learning (BDL) constitutes a promising avenue, offering advantages across these diverse settings. This paper posits that BDL can elevate the capabilities of deep learning. It revisits the strengths of BDL, acknowledges existing challenges, and highlights some exciting research avenues aimed at addressing these obstacles. Looking ahead, the discussion focuses on possible ways to combine large-scale foundation models with BDL to unlock their full potential.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Frequency-dependent dielectric constant prediction of polymers using machine learning

引用

npj Computational Materials 2020年第1期6卷 1147-1155页

作者： Lihua Chen Chiho Kim Rohit Batra Jordan P.Lightstone Chao Wu Zongze Li Ajinkya A.Deshmukh Yifei Wang Huan D.Tran Priya Vashishta Gregory A.Sotzing Yang Cao Rampi Ramprasad School of Materials Science and Engineering Georgia Institute of Technology771 Ferst Drive NWAtlantaGA 30332USA Electrical and Computer Engineering University of Connecticut371 Fairfield WayStorrsCT 06269USA Polymer Program Institute of Material ScienceUniversity of Connecticut97 North Eagleville RoadStorrsCT 06269USA Collaboratory for Advanced Computing and Simulations University of Southern CaliforniaLos AngelesCA 90089-0242USA

The dielectric constant(ϵ)is a critical parameter utilized in the design of polymeric dielectrics for energy storage capacitors,microelectronic devices,and high-voltage ***,agile discovery of polymer dielectrics with desirableϵremains a challenge,especially for high-energy,high-temperature *** aid accelerated polymer dielectrics discovery,we have developed a machine-learning(ML)-based model to instantly and accurately predict the frequency-dependentϵof polymers with the frequency range spanning 15 orders of *** model is trained using a dataset of 1210 experimentally measuredϵvalues at different frequencies,an advanced polymer fingerprinting scheme and the Gaussian process regression algorithm.

关键词： dielectric constant polymer

来源：评论

学校读者我要写书评

暂无评论

Quantum Atomic Matter Near Two-Dimensional Materials in Microgravity

arXiv

引用

arXiv 2023年

作者： Maestro, Adrian Del Kim, Sang Wook Bigelow, Nicholas P. Thompson, Robert J. Kotov, Valeri N. Department of Physics and Astronomy Min H. Kao Department of Electrical Engineering and Computer Science Institute for Advanced Materials and Manufacturing University of Tennessee KnoxvilleTN37996 United States Department of Physics and Materials Science Program University of Vermont BurlingtonVT05405 United States Department of Physics and Astronomy Institute of Optics Center for Coherence and Quantum Optics University of Rochester RochesterNY14627 United States Jet Propulsion Laboratory California Institute of Technology PasadenaCA91109 United States

Novel two-dimensional (2D) atomically flat materials, such as graphene and transition-metal dichalcogenides, exhibit unconventional Dirac electronic spectra. We propose to effectively engineer their interactions with cold atoms in microgravity, leading to a synergy between complex electronic and atomic collective quantum phases and phenomena. Dirac materials are susceptible to manipulation and quantum engineering via changes in their electronic properties by application of strain, doping with carriers, adjustment of their dielectric environment, etc. Consequently the interaction of atoms with such materials, namely the van der Waals / Casimir-Polder interaction, can be effectively manipulated, leading to the potential observation of physical effects such as Quantum Reflection off atomically thin materials and confined Bose-Einstein Condensate (BEC) frequency shifts. Copyright © 2023, The Authors. All rights reserved.

关键词： Transition metals

来源：评论

学校读者我要写书评

暂无评论

Optogenetic Neural Probes: Fiberless, High-Density, Artifact-Free Neuromodulation : (Invited)

Optogenetic Neural Probes: Fiberless, High-Density, Artifact...

引用

International Electron Devices Meeting (IEDM)

作者： Eunah Ko Kanghwan Kim Mihály Vöröslakos Sungjin Oh György Buzsáki Kensall D. Wise Euisk Yoon Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor MI USA Center for BioMicrosystems Brain Science Institute Korea Institute of Science and Technology Seoul Korea Neuroscience Institute Langone Medical Center New York University New York NY USA Department of Biomedical Engineering University of Michigan Ann Arbor MI USA Center for Nanomedicine Institute for Basic Science (IBS) and Graduate Program of Nano Biomedical Engineering (Nano BME) Advanced Science Institute Yonsei University Seoul Korea

ISBN: (纸本)9781665489607

Evolution of “Michigan Probes” has enabled unraveling the connectivity of neurons at cellular resolution and their dynamic interaction within and across brain areas that underlie behavioral and cognitive functions. Recently, micro-LEDs were monolithically integrated for optogenetic neuromodulation at scale without requiring external optical fiber connection. The ‘hectoSTAR’ micro-LED optoelectrode features 256 recording electrodes and 128 stimulation micro-LEDs in four silicon micro-needle shanks, covering a large volume with 1.3-mm × 0.9-mm cross-sectional area located as deep as 6 mm inside the brain. Technical challenges to overcome in scaling of optogenetic probes will be discussed, followed by future direction.

关键词： Optical fibers Electrodes Brain Optogenetics Silicon Recording Optical fiber devices

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：