检索结果-内蒙古大学图书馆

Dimensionality reduction in 3D causal deep learning for neuroimage generation: an evaluation study

Journal of Medical Imaging 2025年第2期12卷

作者： Ohara, Erik Y. Vigneshwaran, Vibujithan Souza, Raissa Vamosi, Finn G. Wilms, Matthias Forkert, Nils D. University of Calgary Biomedical Engineering Graduate Program CalgaryAB Canada University of Calgary Department of Radiology CalgaryAB Canada University of Calgary Hotchkiss Brain Institute CalgaryAB Canada University of Calgary Alberta Children's Hospital Research Institute CalgaryAB Canada University of Calgary Department of Computer Science CalgaryAB Canada University of Calgary Departments of Pediatrics and Community Health Sciences CalgaryAB Canada

Purpose: Causal deep learning (DL) using normalizing flows allows the generation of true counterfactual images, which is relevant for many medical applications such as explainability of decisions, image harmonization, and in-silico studies. However, such models are computationally expensive when applied directly to high-resolution 3D images and, therefore, require image dimensionality reduction (DR) to efficiently process the data. The goal of this work was to compare how different DR methods affect counterfactual neuroimage generation. Approach: Five DR techniques [2D principal component analysis (PCA), 2.5D PCA, 3D PCA, autoencoder, and Vector Quantised-Variational AutoEncoder] were applied to 23,692 3D brain images to create low-dimensional representations for causal DL model training. Convolutional neural networks were used to quantitatively evaluate age and sex changes on the counterfactual neuroimages. Age alterations were measured using the mean absolute error (MAE), whereas sex changes were assessed via classification accuracy. Results: The 2.5D PCA technique achieved the lowest MAE of 4.16 when changing the age variable of an original image. When sex was changed, the autoencoder embedding led to the highest classification accuracy of 97.84% while also significantly impacting the age variable predictions, increasing the MAE to 5.24 years. Overall, 3D PCA provided the best balance, with an age prediction MAE of 4.57 years while maintaining 94.01% sex classification accuracy when altering the age variable and 94.73% sex classification accuracy and the lowest age prediction MAE (3.84 years) when altering the sex variable. Conclusions: 3D PCA appears to be the best-suited DR method for causal neuroimage analysis. © 2025 Society of Photo-Optical Instrumentation Engineers (SPIE).

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Contract-Inspired Contest Theory for Controllable Image Generation in Mobile Edge Metaverse

引用

IEEE Transactions on Mobile Computing 2025年

作者： Liu, Guangyuan Du, Hongyang Wang, Jiacheng Niyato, Dusit Kim, Dong In Nanyang Technological University College of Computing and Data Science Energy Research Institute @ NTU Interdisciplinary Graduate Program Singapore University of Hong Kong Department of Electrical and Electronic Engineering Hong Kong Hong Kong Nanyang Technological University College of Computing and Data Science Singapore Sungkyunkwan University Department of Electrical and Computer Engineering Korea Republic of

The rapid advancement of immersive technologies has propelled the development of the Metaverse, where the convergence of virtual and physical realities necessitates the generation of high-quality, photorealistic images to enhance user experience. However, generating these images, especially through Generative Diffusion Models (GDMs), in mobile edge computing environments presents significant challenges due to the limited computing resources of edge devices and the dynamic nature of wireless networks. This paper proposes a novel framework that integrates contract-inspired contest theory, Deep Reinforcement Learning (DRL), and GDMs to optimize image generation in these resource-constrained environments. The framework addresses the critical challenges of resource allocation and semantic data transmission quality by incentivizing edge devices to efficiently transmit high-quality semantic data, which is essential for creating realistic and immersive images. The use of contest and contract theory ensures that edge devices are motivated to allocate resources effectively, while DRL dynamically adjusts to network conditions, optimizing the overall image generation process. Experimental results demonstrate that the proposed approach not only improves the quality of generated images but also achieves superior convergence speed and stability compared to traditional methods. This makes the framework particularly effective for optimizing complex resource allocation tasks in mobile edge Metaverse applications, offering enhanced performance and efficiency in creating immersive virtual environments. © 2002-2012 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Design of a Framework Based on MCDM and Data Analytics for Improving the Inventory Management of Supplies for Clinical Studies: A Case Study in a Research Center of a High Complexity Clinic 26th

Design of a Framework Based on MCDM and Data Analytics for I...

引用

26th International Conference on Human-computer Interaction, HCII 2024

作者： Jiménez-Delgado, Genett Isabel Aslan, Imran Hernández-Palma, Hugo Orozco Bohorquez, Mario Acosta Ortega, Felipe Plazas-Alvarado, Jonny Jiménez-Coronado, Angélica Roncallo-Pichon, Alberto Morales-Espinosa, Roberto Department of Industrial Engineering Institución Universitaria de Barranquilla IUB Barranquilla Colombia Faculty of Health Sciences Bingöl University Bingöl12000 Turkey Faculty of Engineering Industrial Engineering Program Corporación Universitaria Iberoamericana IBERO Bogotá Colombia Department of Computer Science and Electronics Universidad de la Costa CUC Barranquilla Colombia Faculty of Economic Accounting and Administrative Sciences Business Administration Program Fundación Universitaria de Popayan Popayan Colombia Bogotá Colombia Department of Business Transformation - Business Administration Program Corporación Unificada Nacional de Educación Superior – CUN Bogotá Colombia Faculty of Economic Administrative and Accounting Sciences. Accounting Program Corporación Universitaria Americana Barranquilla Colombia International Business Program Fundación Universitaria CEIPA Barranquilla Colombia

ISBN: (纸本)9783031768088

Inventory management in the health sector, specifically in the pharmaceutical service, represents a high percentage of logistics costs, putting pressure on health institutions to optimize inventory management to guarantee the availability of supplies. On the other hand, different regulations worldwide establish the adoption of mechanisms and policies for adequate inventory management, a situation that in low- and middle-income countries is restricted by resource limitations and the low implementation of robust techniques and methodologies. Different applications of models for inventory management have been identified in the literature, such as optimization models, Lean tools, and multicriteria decision-making methods. However, integrated approaches to optimize demand management, ordering, and controlling pharmaceutical services supplies are still under development. Therefore, the present study proposes a three-phase hybrid approach based on MCDM techniques and data analytics to improve inventory management of the pharmaceutical service in a health research center. The first stage consisted of characterizing the process to identify aspects for improvement. In the second stage, a multicriteria ABC classification model based on F-AHP and TOPSIS was applied to classify laboratory supplies for three selected clinical studies. Furthermore, the appropriate forecasting method was chosen for each clinical study, and a combined model (P model and FEFO model) was applied to establish the reorder point. Then, strategies, mechanisms, and policies were proposed to improve inventory management and redesign the process flow. As the main results, a multicriteria ABC method was obtained to classify laboratory supplies, taking into account Rotation (GW = 0.512), Criticality (GW = 0.286), and Availability (GW = 0.203). On the other hand, through data analysis and regression models, the exponential smoothing model with α = 0.10 was identified as the most convenient forecasting model, as

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

A Finite Difference Method for a Normalized Time-Fractional Black–Scholes Equation

引用

International Journal of Applied and Computational Mathematics 2025年第3期11卷 1-17页

作者： Nam, Yunjae Wang, Jian Lee, Chaeyoung Choi, Yongho Bang, Minjoon Li, Zhengang Kim, Junseok Program in Actuarial Science and Financial Engineering Korea University Seoul 02841 South Korea School of Mathematics and Statistics Nanjing University of Information Science and Technology Nanjing 210044 China Department of Mathematics Kyonggi University Suwon 16227 South Korea Computer and Information Engineering Daegu University Gyeongsan 38453 South Korea Department of Mathematics Korea University Seoul 02841 South Korea

In this article, we propose a normalized time-fractional Black–Scholes (TFBS) equation. The proposed model uses a normalized time-fractional derivative which has a distinctive feature wherein a weight function possesses the property that its integral with respect to time is always equal to one. This feature ensures a well-balanced integration over time and provides a fair comparison between different fractional orders. An implicit finite difference method is used for the numerical solution of the TFBS equation. We perform several standard numerical tests to examine the effect of the fractional parameter on the option pricing. These experiments are designed to investigate how variations in the fractional parameter influence pricing outcomes and provide valuable insights into the model’s behavior under different conditions. The computational results demonstrate the model’s potential for capturing more intricate market dynamics, which makes the proposed model a promising tool for financial analysis. In the appendix, we provide a computer program that implements the numerical methods discussed in the paper for interested readers. © The Author(s), under exclusive licence to Springer Nature India Private Limited 2025.

关键词： Implicit finite difference method Memory effect Normalized time-fractional Black–Scholes equation

来源：评论

学校读者我要写书评

暂无评论

Interconnected Through Robotic System in English Foreign Language Education 5th

Interconnected Through Robotic System in English Foreign Lan...

引用

5th International Conference on Advances in Information Communication Technology and Computing, AICTC 2024

作者： Muthmainnah, M. de Barros Cardoso, Luís Miguel Oliveira Kaur, Dalwinder Burhamzah, Muftihaturrahmah Aeni, Nur Al Yakin, Ahmad Sharma, Aditi Teacher Training and Education Faculty Indonesian Language Study Program Universitas Al Asyariah Mandar Polewali Mandar Indonesia Portugal Department of Languages and Communication Sciences Polytechnic Institute of Portalegre Portalegre Portugal Manipal Globalnxt University Kuala Lumpur Malaysia English Study Program Universitas Negeri Makassar Makassar Indonesia Teacher Training and Education Faculty Civic Education Study Program Universitas Al Asyariah Mandar Polewali Mandar Indonesia Department of Computer Science and Engineering Symbiosis Institute of Technology Symbiosis International [Deemed University Pune India

ISBN: (纸本)9789819761050

Robots have become increasingly important in a variety of life domains as a result of the rapid advancement of technology. Additionally, robots are employed in education as teaching assistants in science, art, and language courses. This research aims to explore the potential of robotic systems as a multipurpose tool for increasing cultural awareness, language proficiency, and communicative competence in the GenAI era. Language games, conversation simulations, and real-time feedback mechanisms are just a few examples of interactive scenarios enabled by virtual robot systems or tutor robots that enable immersive language experiences that go beyond the limitations of conventional schooling. This research contributes knowledge that explores how AI can be used to personalize language teaching according to the needs and learning styles of each student in higher education. The total population of undergraduate students involved in this research was 350 for the 2023 academic year, with 24 students selected purposefully based on sample characteristics from this group who were exposed to using AI for one semester. The research method used is a mix method with quantitative analysis of the results of surveys and interviews with students who are known to have given positive responses and proposes a comprehensive strategy for using AI robot technology in EFL classrooms, which can significantly improve effective learning outcomes. The survey results also show that if educators have a solid understanding of the relationship between linguistic acquisition and technological advances, they will be better prepared to design engaging, individualized lessons that prepare their students to use the language effectively in real-world contexts. The robot-assisted language learning (RALL) approach used in this study, with the integration of robots in the classroom, has the potential to change the way people learn languages to make it more interesting, fun, and motivating, increase engagement

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

KNU-DTI: KNowledge United Drug-Target Interaction prediction

引用

computers in Biology and Medicine 2025年 189卷 109927-109927页

作者： Heo, Ryong Lee, Dahyeon Kim, Byung Ju Seo, Sangmin Park, Sanghyun Park, Chihyun Interdisciplinary Graduate Program in Medical Bigdata Convergence Kangwon National University Gangwon-do Chuncheon-si24341 Korea Republic of Department of Data Science Kangwon National University Korea Republic of UBLBio Corporation Yeongtong-ro 237 Gyeonggi-do Suwon16679 Korea Republic of Department of Computer Science Yonsei University Yonsei-ro 50 Seodaemun-gu Seoul03722 Korea Republic of Department of Computer Science and Engineering Kangwon National University Korea Republic of

Motivation: Accurately predicting drug-target protein interactions (DTI) is a cornerstone of drug discovery, enabling the identification of potential therapeutic compounds. Sequence-based prediction models, despite their simplicity, hold great promise in extracting essential information directly from raw sequences. However, the focus in recent DTI studies has increasingly shifted toward enhancing algorithmic complexity, often at the expense of fully leveraging robust sequence representation learning methods. This shift has led to the underestimation and gradual neglect of methodologies aimed at effectively capturing discriminative features from sequences. Our work seeks to address this oversight by emphasizing the value of well-constructed sequence representation algorithms, demonstrating that even with simple interaction mapping algorithm techniques, accurate DTI models can be achieved. By prioritizing meaningful information extraction over excessive model complexity, we aim to advance the development of practical and generalizable DTI prediction frameworks. Results: We developed the KNowledge Uniting DTI model (KNU-DTI), which retrieves structural information and unites them. Protein structural properties were obtained using structural property sequence (SPS). Extended-connectivity fingerprint (ECFP) was used to estimate the structure-activity relationship in molecules. Including these two features, a total of five latent vectors were derived from protein and molecule via various neural networks and integrated by elemental-wise addition to predict binding interactions or affinity. Using four test concepts to evaluate the model, we show that the model outperforms recently published competitors. Finally, a case study indicated that our model has a competitive edge over existing docking simulations in some cases. © 2025

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Leaf Disease Segmentation Using Uunet++ Architecture 3rd

Leaf Disease Segmentation Using Uunet++ Architecture

引用

3rd International Conference on Trends in Electronics and Health Informatics, TEHI 2023

作者： Farooqui, Nafees Akhter Mishra, Amit Kumar Ray, Kanad Mallik, Saurav Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Guntur India Karnataka Bengaluru India Department of Physics Amity School of Applied Sciences Amity University Rajasthan Rajasthan Jaipur India Amity Cognitive Computing and Brain Informatics Centre Amity University Rajasthan Rajasthan303002 India Department of Environmental Health Harvard T H Chan School of Public Health BostonMA02115 United States Pharmacology & Toxicology University of Arizona TucsonAZ85721 United States

ISBN: (纸本)9789819739363

Segmentation of leaves is an initial step in image-based plant phenotyping, which has received more attention recently. Leaf segmentation shows features of the leaf and growth stages at the leaf level. Due to the significant overlapping between leaves and fluctuating environmental circumstances, such as intensity change and blur due to wind, segmentation of plant tissues like leaves is a most important issue in plant phenotyping. The leaf segmentation work has more complicated problems, such as leaf surface, genotypes, length, structure, and thickness variability. This study proposes an ultra-modern deep gaining knowledge of architectures: UUNet++, a convolutional neural network for advance segmentation. A vital assessment is done using computer Vision for Plant Phenotyping dataset (CVPPP). The plant phenotyping is performed on tobacco and Arabidopsis leaf of RGB images from plant village dataset. The proposed model needs less space as compared to the main UNet architecture. In contrast to typical deep learning image sets, this dataset contains a limited number of samples. Despite that, we achieve exceptional results in leaf segmentation, specifically in distinguishing the interior of leaves from the binary segmentation of the entire leaf. Furthermore, studies are necessary to accurately quantify the number of leaves. Without reducing performance measures, the disease classification inferences time is extremely efficient and accurate. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

Explanations of Deep Language Models Explain Language Representations in the Brain

arXiv

引用

arXiv 2025年

作者： Rahimi, Maryam Yaghoobzadeh, Yadollah Daliri, Mohammad Reza Biomedical Engineering Department School of Electrical Engineering Iran University of Science and Technology Tehran Iran Electrical and Computer Engineering Department University of Tehran Tehran Iran School of Cognitive Sciences Institute for Research in Fundamental Sciences Tehran Iran Tehran Institute for Advanced Studies Khatam University Tehran Iran

Recent advances in artificial intelligence have given rise to large language models (LLMs) that not only achieve human-like performance but also share computational principles with the brain’s language processing mechanisms. While previous research has primarily focused on aligning LLMs’ internal representations with neural activity, we introduce a novel approach that leverages explainable AI (XAI) methods to forge deeper connections between the two domains. Using attribution methods, we quantified how preceding words contribute to an LLM’s next-word predictions and employed these explanations to predict fMRI recordings from participants listening to the same narratives. Our findings demonstrate that attribution methods robustly predict brain activity across the language network, surpassing traditional internal representations in early language areas. This alignment is hierarchical: early-layer explanations correspond to the initial stages of language processing in the brain, while later layers align with more advanced stages. Moreover, the layers more influential on LLM next-word prediction—those with higher attribution scores—exhibited stronger alignment with neural activity. This work establishes a bidirectional bridge between AI and neuroscience. First, we demonstrate that attribution methods offer a powerful lens for investigating the neural mechanisms of language comprehension, revealing how meaning emerges from preceding context. Second, we propose using brain alignment as a metric to evaluate the validity of attribution methods, providing a framework for assessing their biological plausibility. © 2025, CC BY-SA.

关键词： Computational neuroscience

来源：评论

学校读者我要写书评

暂无评论

Porous silicon on paper sensors: Factors affecting biosensing performance 17

Porous silicon on paper sensors: Factors affecting biosensin...

引用

Frontiers in Biological Detection: From Nanosensors to Systems XVII 2025

作者： An, Huijin Laibinis, Paul E. Locke, Andrea K. Weiss, Sharon M. Interdisciplinary Material Science Program Vanderbilt University NashvilleTN37235 United States Department of Electrical and Computer Engineering Vanderbilt University NashvilleTN37235 United States Department of Chemical and Biomolecular Engineering Vanderbilt University NashvilleTN37235 United States Department of Chemistry Vanderbilt University NashvilleTN37235 United States Department of Biomedical Engineering Vanderbilt University NashvilleTN37235 United States

ISBN: (纸本)9781510684249

A paper-based biosensor integrating a functionalized porous silicon (PSi) membrane as the active sensing element for quantifiable protein detection has been developed. For similar short-time exposures to an analyte, improved molecular transport in PSi membranes when on paper leads to larger signal changes compared to traditional PSi films that remain on a silicon substrate. In this work, we discuss controlling the incubation time of the analyte and the overall testing time of the sensor by incorporating different combinations of wicking and absorbent paper beneath the PSi membrane. With this control, the PSi-on-paper sensor platform has the potential to serve as an effective low-cost rapid diagnostic test with highly sensitive, quantitative readout for a wide range of analytes. © 2025 SPIE.

关键词： Porous silicon

来源：评论

学校读者我要写书评

暂无评论

The growing memristor industry

引用

Nature 2025年第8059期640卷 613-622页

作者： Lanza, Mario Pazos, Sebastian Aguirre, Fernando Sebastian, Abu Le Gallo, Manuel Alam, Syed M. Ikegawa, Sumio Yang, J. Joshua Vianello, Elisa Chang, Meng-Fan Molas, Gabriel Naveh, Ishai Ielmini, Daniele Liu, Ming Roldan, Juan B. Department of Materials Science and Engineering National University of Singapore Singapore Singapore Institute for Functional Intelligent Materials National University of Singapore Singapore Singapore Centre for Advanced 2D Materials (CA2DM) National University of Singapore Singapore Singapore Materials Science and Engineering Program Physical Science and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia Intrinsic Semiconductor Technologies London United Kingdom IBM Research – Zurich Rüschlikon Switzerland Everspin Technologies Chandler AZ United States Department of Electrical and Computer Engineering University of Southern California Los Angeles CA United States CEA-Leti Université Grenoble Alpes Grenoble France Department of Electrical Engineering National Tsing Hua University Hsinchu Taiwan Weebit Nano Hod Hasharon Israel Dipartimento di Elettronica Informazione e Bioingegneria (DEIB) Politecnico di Milano and *** Milano Italy Key Laboratory of Microelectronic Devices and Integrated Technology Institute of Microelectronics Chinese Academy of Sciences Beijing China Departamento de Electrónica y Tecnología de Computadores Universidad de Granada Facultad de Ciencias Granada Spain

The semiconductor industry is experiencing an accelerated transformation to overcome the scaling limits of the transistor and to adapt to new requirements in terms of data storage and computation, especially driven by artificial intelligence applications and the Internet of Things. In this process, new materials, devices, integration strategies and system architectures are being developed and optimized. Among them, memristive devices and circuits—memristors are two-terminal memory devices that can also mimic some basic bioelectronic functions—offer a potential approach to create more compact, energy-efficient or better-performing systems. The memristor industry is growing quickly, raising abundant capital investment, creating new jobs and placing advanced products in the market. Here we analyse the status and prospects of the memristor industry, focusing on memristor-based products that are already commercially available, prototypes with a high technological readiness level that might affect the market in the near future, and discuss obstacles and pathways to their implementation. © Springer Nature Limited 2025.

关键词：

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：