检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Nohel, Michal Ulrich, Constantin Suprijadi, Jonathan Wald, Tassilo Maier-Hein, Klaus Division of Medical Image Computing Heidelberg Germany Department of Biomedical Engineering Faculty of Electrical Engineering and Communication Brno University of Technology Brno Czech Republic University hospital Ostrava Department of Deputy director for science research and education Czech Republic Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Heidelberg Germany NCT Heidelberg A partnership between DKFZ University Medical Center Heidelberg Germany Medical Faculty Heidelberg University of Heidelberg Heidelberg Germany Faculty of Mathematics and Computer Science Heidelberg University Germany

This study presents an open-source toolkit to address critical challenges in preprocessing data for self-supervised learning (SSL) for 3D medical imaging, focusing on data privacy and computational efficiency. The toolkit comprises two main components: a segmentation network that delineates foreground regions to optimize data sampling and thus reduce training time, and a segmentation network that identifies anonymized regions, preventing erroneous supervision in reconstructionbased SSL methods. Experimental results demonstrate high robustness, with mean Dice scores exceeding 98.5 across all anonymization methods and surpassing 99.5 for foreground segmentation tasks, highlighting the toolkit's efficacy in supporting SSL applications in 3D medical imaging for both CT and MRI images. The weights and code is available at https://***/MIC-DKFZ/Foreground-and- Anonymization-Area-Segmentation. © 2025, CC BY.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Foundation-Model-Boosted Multimodal Learning for fMRI-based Neuropathic Pain Drug Response Prediction

arXiv

引用

arXiv 2025年

作者： Fan, Wenrui Rizky, L.M. Riza Zhang, Jiayang Chen, Chen Lu, Haiping Teh, Kevin Selvarajah, Dinesh Zhou, Shuo School of Computer Science University of Sheffield Sheffield United Kingdom Centre for Machine Intelligence University of Sheffield Sheffield United Kingdom Academic Unit of Radiology University of Sheffield Sheffield United Kingdom Diabetes Research Unit Royal Hallamshire Hospital Sheffield United Kingdom Division of Clinical Medicine University of Sheffield Sheffield United Kingdom Department of Computing Imperial College London London United Kingdom

Neuropathic pain, affecting up to 10% of adults, remains difficult to treat due to limited therapeutic efficacy and tolerability. Although resting-state functional MRI (rs-fMRI) is a promising noninvasive measurement of brain biomarkers to predict drug response in therapeutic development, the complexity of fMRI demands machine learning models with substantial capacity. However, extreme data scarcity in neuropathic pain research limits the application of high-capacity models. To address the challenge of data scarcity, we propose FMMTC, a Foundation-Model-boosted Multimodal learning framework for fMRI-based neuropathic pain drug response prediction, which leverages both internal multimodal information in pain-specific data and external knowledge from large pain-agnostic data. Specifically, to maximize the value of limited pain-specific data, FMMTC integrates complementary information from two rs-fMRI modalities: Time series and functional Connectivity. FMMTC is further boosted by an fMRI foundation model with its external knowledge from extensive pain-agnostic fMRI datasets enriching limited pain-specific information. Evaluations with an in-house dataset and a public dataset from OpenNeuro demonstrate FMMTC’s superior representation ability, generalizability, and cross-dataset adaptability over existing unimodal fMRI models that only consider one of the rs-fMRI modalities. The ablation study validates the effectiveness of multimodal learning and foundation-model-powered external knowledge transfer in FMMTC. An integrated gradient-based interpretation study explains how FMMTC’s cross-dataset dynamic behaviors enhance its adaptability. In conclusion, FMMTC boosts clinical trials in neuropathic pain therapeutic development by accurately predicting drug responses to improve the participant stratification efficiency. The code is released on https://***/Shef-AIRE/FMM_TC. Copyright © 2025, The Authors. All rights reserved.

关键词： Drug discovery

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of image mosaicing techniques for aerial agriculture field imaging

引用

European Journal of Remote Sensing 2025年第1期58卷

作者： Maria John S. Santhanalakshmi J Amudha Jianfeng Zhou a Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidhyapeetham Bengaluru India b Division of Plant Science and Technology University of Missouri Columbia MO USA

ABSTRACTUAVs that are outfitted with advanced image sensors offer a flexible and cost-efficient means of obtaining cohesive, inclusive, and precise visual depictions of regions. The obtained visual data, however, frequently comprises fragmented data as a result of the restricted perspective of individual images. To address this constraint, image mosaicing techniques are utilized to seamlessly merge various images, resulting in a thorough and uninterrupted depiction of the agricultural environment. The objective of this work is to evaluate and compare image mosaicing techniques, focusing primarily on agricultural datasets. It uncovers and exposes the constraints that exist in existing algorithms. The dataset of maize crop acquired from Phantom drones in the farms of Centralia, Missouri, USA, is utilized for this work. The Aerial images are used to evaluate distinctive feature-based and direct pixel-based mosaicing methods. The research analyzes four performance metrics, which consist of the Structural Similarity Index (SSIM) and Root Mean Square (RMS) error, together with Standard Deviation (SD) and CPU computational time. Analysis of Variance was conducted for the texture features of the generated mosaics. Several experimental findings show how the accuracy-performance-visual quality relationship affects the selection of suitable methods for real-time agricultural dataset. The research findings provide knowledge to select the best mosaicing solutions that will benefit crop health assessment and yield estimation applications.

关键词： Image stitching aerial images unmanned ariel vehicle (UAV) remote sensing agriculture precision agriculture

来源：评论

学校读者我要写书评

暂无评论

Foundation Models for Atomistic Simulation of Chemistry and Materials

arXiv

引用

arXiv 2025年

作者： Yuan, Eric C.-Y. Liu, Yunsheng Chen, Junmin Zhong, Peichen Raja, Sanjeev Kreiman, Tobias Vargas, Santiago Xu, Wenbin Head-Gordon, Martin Yang, Chao Blau, Samuel M. Cheng, Bingqing Krishnapriyan, Aditi Head-Gordon, Teresa Kenneth S. Pitzer Theory Center Department of Chemistry United States Department of Chemical and Biomolecular Engineering United States Electrical Engineering and Computer Science United States Bakar Institute of Digital Materials for the Planet University of California BerkeleyCA94720 United States Chemical Sciences Division United States Applied Mathematics and Computational Research Division United States Energy Technologies Area United States National Energy Research Scientific Computing Center Lawrence Berkeley National Laboratory BerkeleyCA94720 United States

Given the power of large language and large vision models, it is of profound and fundamental interest to ask if a foundational model based on data and parameter scaling laws and pre-training strategies is possible for learned simulations of chemistry and materials. The scaling of large and diverse datasets and highly expressive architectures for chemical and materials sciences should result in a foundation model that is more efficient and broadly transferable, robust to out-of-distribution challenges, and easily fine-tuned to a variety of downstream observables, when compared to specific training from scratch on targeted applications in atomistic simulation. In this Perspective we aim to cover the rapidly advancing field of machine learned interatomic potentials (MLIP), and to illustrate a path to create chemistry and materials MLIP foundation models at larger scale. © 2025, CC BY-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A multimodal machine learning model for bipolar disorder mania classification: Insights from acoustic, linguistic, and visual cues

引用

Intelligence-Based Medicine 2025年 11卷 100223-100223页

作者： Murugavel, Kiruthiga Devi R, Parthasarathy Mathivanan, Sandeep Kumar Srinivasan, Saravanan Shivahare, Basu Dev Shah, Mohd Asif Department of Computer Science and Engineering SRM Institute of Science and Technology Vadapalani Chennai 600026 India Department of Computer Science & Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India School of Computing Science and Engineering Galgotias University Greater Noida 203201 India Department of Economics Kardan University Parwane Du Kabul 1001 Afghanistan Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura 140401 India Chitkara Centre for Research and Development Chitkara University Baddi Himachal Pradesh 174103 India Division of Research and Development Lovely Professional University Punjab Phagwara 144001 India

Mood fluctuations that can vary from manic to depressive states are a symptom of a disease known as bipolar disorder, which affects mental health. Interviews with patients and gathering information from their families are essential steps in the diagnostic process for bipolar disorder. Automated approaches for treating bipolar disorder are also being explored. In mental health prevention and care, machine learning techniques (ML) are increasingly used to detect and treat diseases. With frequently analyzed human behaviour patterns, identified symptoms, and risk factors as various parameters of the dataset, predictions can be made for improving traditional diagnosis methods. In this study, A Multimodal Fusion System was developed based on an auditory, linguistic, and visual patient recording as an input dataset for a three-stage mania classification decision system. Deep Denoising Autoencoders (DDAEs) are introduced to learn common representations across five modalities: acoustic characteristics, eye gaze, facial landmarks, head posture, and Facial Action Units (FAUs). This is done in particular for the audio-visual modality. The distributed representations and the transient information during each recording session are eventually encoded into Fisher Vectors (FVs), which capture the representations. Once the Fisher Vectors (FVs) and document embeddings are integrated, a Multi-Task Neural Network is used to perform the classification task, while mitigating overfitting issues caused by the limited size of the bipolar disorder dataset. The study introduces Deep Denoising Autoencoders (DDAEs) for cross-modal representation learning and utilizes Fisher Vectors with Multi-Task Neural Networks, enhancing diagnostic accuracy while highlighting the benefits of multimodal fusion for mental health diagnostics. Achieving an unweighted average recall score of 64.8 %, with the highest AUC-ROC of 0.85 & less interface time of 6.5 ms/sample scores the effectiveness of integrating mult

关键词： Audio-visual modality Bipolar disorder Deep denoising autoencoders (DDAEs) Fisher vectors (FVs) Multimodal

来源：评论

学校读者我要写书评

暂无评论

Iteration space partitioning

引用

FUTURE GENERATION computer SYSTEMS 1997年第5期12卷 421-429页

作者： Bik, AJC Wijshoff, HAG High Performance Computing Division Department of Computer Science Leiden University PO Box 9512 2300 RA Leiden The Netherlands

In this paper, we present a general method to isolate the loop-body of a nested loop for all iterations in a particular polyhedral set. This isolation is done by successively partitioning execution sets of individual DO-loops in the loop, thereby partitioning the iteration space according to the linear inequalities that define the polyhedral set. In particular, this method is useful to perform program simplifications or to support data structure transformations.

关键词： iteration space partitioning loop transformation program restructuring program optimization

来源：评论

学校读者我要写书评

暂无评论

Large Scale Supervised Pretraining For Traumatic Brain Injury Segmentation

arXiv

引用

arXiv 2025年

作者： Ulrich, Constantin Wald, Tassilo Isensee, Fabian Maier-Hein, Klaus H. German Cancer Research Center DKFZ Heidelberg Division of Medical Image Computing Germany Helmholtz Imaging DKFZ Heidelberg Germany Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Heidelberg Germany NCT Heidelberg DKFZ University Medical Center Heidelberg Germany Medical Faculty Heidelberg University of Heidelberg Heidelberg Germany Faculty of Mathematics and Computer Science Heidelberg University Germany

The segmentation of lesions in Moderate to Severe Traumatic Brain Injury (msTBI) presents a significant challenge in neuroimaging due to the diverse characteristics of these lesions, which vary in size, shape, and distribution across brain regions and tissue types. This heterogeneity complicates traditional image processing techniques, resulting in critical errors in tasks such as image registration and brain parcellation. To address these challenges, the AIMS-TBI Segmentation Challenge 2024 aims to advance innovative segmentation algorithms specifically designed for T1-weighted MRI data, the most widely utilized imaging modality in clinical practice. Our proposed solution leverages a large-scale multi-dataset supervised pretraining approach inspired by the MultiTalent method. We train a Resenc L network on a comprehensive collection of datasets covering various anatomical and pathological structures, which equips the model with a robust understanding of brain anatomy and pathology. Following this, the model is fine-tuned on msTBI-specific data to optimize its performance for the unique characteristics of T1-weighted MRI scans and outperforms the baseline without pretraining up to 2 Dice points. © 2025, CC BY.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Theoretical investigation of shock stand-off distance for non-equilibrium flows over spheres

引用

Chinese Journal of Aeronautics 2018年第5期31卷 990-996页

作者： Hua SHEN Chih-Yung WEN Extreme Computing Research Center Computer Electrical and Mathematical Science and Engineering DivisionKing Abdullah University of Science and Technology Department of Mechanical Engineering The Hong Kong Polytechnic University

We derived a theoretical solution of the shock stand-off distance for a non-equilibrium flow over spheres based on Wen and Hornung＇s solution and Olivier＇s solution. Compared with previous approaches, the main advantage of the present approach is allowing an analytic solution without involving any semi-empirical parameter for the whole non-equilibrium flow regimes. The effects of some important physical quantities therefore can be fully revealed via the analytic solution. By combining the current solution with Ideal Dissociating Gas（IDG） model, we investigate the effects of free stream kinetic energy and free stream dissociation level（which can be very different between different facilities） on the shock stand-off distance.

关键词： Gas dynamics Supersonic/hypersonic flow Shock stand-off distant Non-equilibrium flow Blunt body Shock

来源：评论

学校读者我要写书评

暂无评论

High accuracy indoor positioning system using Galois field-based cryptography and hybrid deep learning

引用

Scientific Reports 2025年第1期15卷 1-23页

作者： Hazzazi, Mohammad Mazyad Shukla, Prashant Kumar Shukla, Piyush Kumar Alblehai, Fahad Nooh, Sameer Shah, Mohd Asif Department of Mathematics College of Science King Khalid University Abha 61413 Saudi Arabia Department of Computer Science and Engineering Amity School of Engineering and Technology (ASET) Amity University Mumbai Maharashtra Mumbai 410206 India Computer Science & Engineering Department University Institute of Technology Rajiv Gandhi Proudyogiki Vishwavidyalaya (State Technological University of Madhya Pradesh) Madhya Pradesh Bhopal 462033 India Computer Science Department Community College King Saud University Riyadh 11437 Saudi Arabia Information Systems Department Faculty of Computing and Information Technology King Abdulaziz University Jeddah 22254 Saudi Arabia Department of Economics Kardan University Parwane Du Kabul 1001 Afghanistan Division of Research and Development Lovely Professional University 144001 Punjab Phagwara India Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University 140401 Punjab Rajpura India

In smart manufacturing, logistics, and other inside settings where the Global Positioning System (GPS) doesn’t work, indoor positioning systems (IPS) are essential. Due to environmental complexity, signal noise, and possible data manipulation, traditional IPS techniques struggle with accuracy, resilience, and security. Online and offline phases are distinguished in the suggested indoor location system that employs deep learning and fingerprinting. During the offline phase, mobile devices gather signal strength measurements and contextual data traverse inside settings via Wi-Fi, Bluetooth, and magnetometers. Fingerprint classification using Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering follows the application of signal processing techniques for noise reduction and data augmentation. The online phase involves extracting information to improve the model’s accuracy. These features can be signal-based, spatial–temporal, motion-based, or environmental. The Deep Spatial–Temporal Attention Network (Deep-STAN) is an innovative hybrid model for location classification that combines Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), Long-Short Term Memory (LSTMs), and attention processes. The model hyperparameters are fine-tuned using hybrid optimization to guarantee optimal performance. The work’s main contribution is the incorporation of ECC, an effective encryption and decryption method for signal data, which is based on Galois fields. This cryptographic method is well-suited for real-world applications since it guarantees low-latency operations while simultaneously improving data integrity and confidentiality. In addition, S-box enhances the IPS’s resilience and security by including QR codes for distinct location marking and blockchain technology for safe and immutable storing of positioning data. Moreover, the performance of the suggested model includes an accuracy of 0.9937, precision of 0.987, sensitivity of 0.9898, and

关键词： Blockchain technology Deep learning Fingerprinting Galois field cryptography Hybrid optimization Indoor positioning system QR codes

来源：评论

学校读者我要写书评

暂无评论

Evaluation of carbon based interconnects for digital signalling in printed flexible electronics on sustainable substrates

IEEE Journal on Flexible Electronics

引用

IEEE Journal on Flexible Electronics 2025年

作者： Wang, Zixin Saleh, Mahdi Alwattar, Aula Alfredsson, Maria Horne, Robert J. Ang, Chee S. Condell, Joan Flowers, Emily Matcham, Faith Robinson, Tony Rooksby, John Saha, Sian Rose, Louise Batchelor, John C. Casson, Alexander J. Henry Royce Institute for Advanced Materials Manchester United Kingdom The University of Manchester School of Engineering Department of Electrical and Electronic Engineering Manchester United Kingdom The University of Manchester School of Natural Sciences Department of Chemistry Manchester United Kingdom University of Kent School of Chemistry and Forensic Science Canterbury United Kingdom University of Kent School of Engineering Canterbury United Kingdom University of Kent School of Computing Canterbury United Kingdom Ulster University School of Computing Engineering and Intelligent Systems Derry United Kingdom King’s College London Division of Digital Health and Applied Technology Assessment London United Kingdom University of Sussex School of Psychology Falmer United Kingdom Northumbria University Department of Computer and Information Sciences Newcastle upon Tyne United Kingdom

Printed electronics using flexible substrates are an emerging area, allowing next-generation electronics to conform and flex with different surfaces, from human skin to clothing. In the hybrid integration, or sea-of-rigids, approach, conventional microchips are mounted onto (generally) plastic substrates such as polyethylene naphthalate (PEN), with (typically) printed silver tracks for interconnections between components. An ongoing research direction is to replace plastic substrates with biodegradable substrates and to replace silver tracks with non-heavy metal-based tracks. While the substrates and tracks form only part of an overall system, replacing them is a step towards increased sustainability and helps to meet net-zero goals for printed electronic systems. Previously, several papers have investigated printed carbon tracks for low-frequency analog sensing applications. This paper explores the feasibility of using printed carbon tracks on biodegradable substrates for high-frequency applications such as digital signaling over a Serial-Peripheral Interface (SPI). We investigate the printability, thermal stability, and electrical conductivity of carbon ink screen-printed onto six commercially available sustainable and flexible substrates. Our results demonstrate that multi-layer screen printing substantially reduced the electrical resistance of carbon tracks, enabling SPI communication at frequencies up to 16 MHz with three layers of carbon ink. A Natureflex™ substrate provided the best balance of printability, thermal stability, and electrical performance. Substrates such as greaseproof paper and ClearFilm PU showed potential for flexible electronics, but require further optimization. This study provides valuable insights into selecting and optimizing biodegradable substrates for high-frequency digital systems, supporting the move towards more sustainable printed electronics. © 2022 IEEE.

关键词： Variable frequency oscillators

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：