检索结果-内蒙古大学图书馆

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Lin, Tsung-Wei Arriagada, Sofia Ormazabal Lin, Che Taiwan Taiwan International Graduate Program AIoT Ntu Taiwan Research Center for Information Technology Innovation Academia Sinica Taiwan Department of Electrical Engineering Ntu Taiwan Center for Advanced Computing and Imaging in Biomedicine Ntu Taiwan Smart Medicine and Health Informatics Program Ntu Taiwan

ISBN: (纸本)9798350371499

Providing robust prognosis predictions for cancers with limited data samples remains a challenge for precision oncology. In this study, we propose a novel approach that combines multi-task learning (MTL) and graph neural networks (GNNs) to address this issue. By representing gene-gene interactions as a graph network, our approach leverages multi-task learning to effectively capture the relationships of genes relevant to the oncogenesis and progression of breast, lung, and colon cancer. We demonstrate that our approach improves the cancer prognosis prediction for cancers with fewer samples, such as colon adenocarcinoma, by leveraging the shared gene-gene interactions across different cancer types, obtaining increases in the area under the precision-recall curve (AUPRC) of 24%. Our work contributes to the field of smart healthcare by demonstrating the potential of MTL and GNNs for enhancing cancer prognosis prediction, even with limited data samples. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Convergence analysis of a Schrödinger problem with moving boundary

引用

Mathematics and Computers in Simulation 2025年 238卷 45-64页

作者： Alfaro Vigo, Daniel G. Gomes, Daniele C.R. do Carmo, Bruno A. Rincon, Mauro A. Institute of Computing Federal University of Rio de Janeiro Caixa Postal 68.530 RJ Rio de JaneiroCEP 21941-590 Brazil Graduate Program in Informatics Federal University of Rio de Janeiro Caixa Postal 68.530 RJ Rio de JaneiroCEP 21941-590 Brazil

In this article, we present the mathematical analysis of the convergence of the linearized Crank–Nicolson Galerkin method for a nonlinear Schrödinger problem related to a domain with a moving boundary. The convergence analysis of the numerical method is carried out for both semidiscrete and fully discrete problems. We establish an optimal error estimate in the L2-norm with order O(τ2+hs),2≤s≤r, where h is the finite element mesh size, τ is the time step, and r−1 represents the degree of the finite element polynomial basis. Numerical simulations are provided to confirm the consistency between theoretical and numerical results, validating the method and the order of convergence for different degrees p≥1 of the Lagrange polynomials and also for Hermite polynomials (degree p=3), which form the basis of the approximate solution. © 2025 International Association for Mathematics and Computers in Simulation (IMACS)

关键词： Convergence of numerical methods

来源：评论

学校读者我要写书评

暂无评论

Mineralogical Classification of Sedimentary Rocks by Spectral Matching Techniques Based on Library and Field-Work References 14

Mineralogical Classification of Sedimentary Rocks by Spectra...

引用

14th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, WHISPERS 2024

作者： Zanotta, Daniel C. De Souza, Lais V. De Souza, Marcelo K. Ayres, Alysson S. Sales, Vinicius F. Racolte, Graciela R. Ibanez, Delano M. Silveira, Luiz G. Veronez, Mauricio R. UNISINOS Vizlab X-Reality and GeoInformatics Lab RS São Leopoldo Brazil Graduate Program in Applied Computing Vale do Rio dos Sinos University RS São Leopoldo Brazil RJ Brazil

ISBN: (纸本)9798331513139

Sedimentary rocks are of great importance for the oil and gas industry. Spectral matching using known references made on hyperspectral images is one of the most rapid and cost effective alternatives for the detailed analysis in these areas, since they can adequately catch the specific absorption features of the multiple minerals available. In many initiatives, scientists run the methods with standard spectral references, usually from spectral libraries or samples from other places. However, for the success of their application, they must be used along with spectral references that accurately describe the actual constituents of the surface. In this paper we scrutinize three different ways for mineralogical mapping performed by spectral matching techniques. The results showed that using reference spectra from samples collected directly on the surveyed environment can considerably improve the results, reaching high scores, pointing out that many places share common substances, but each specific material has particular differences that cannot be generalized. © 2024 IEEE.

关键词： Gas industry

来源：评论

学校读者我要写书评

暂无评论

Fine Tuning Swin Transformer Based Pretrained Model for Microscopic Fungi Images Classification 11

Fine Tuning Swin Transformer Based Pretrained Model for Micr...

引用

11th International Conference on Computer, Control, Informatics and its Applications, IC3INA 2024

作者： Anggara, Muchamad Galih Hindasyah, Ahmad Amda, Julfa Muhammad Waskita, A.A. Graduate Program of Informatics Engineering Universitas Pamulang Pamulang Indonesia Research Center for Computing National Research and Innovation Agency Cibinong Indonesia Research Center for Data and Information Sciences National Research and Innovation Agency Bandung Indonesia

ISBN: (纸本)9798331542313

Accurate image classification of microscopic pathogenic fungi is a challenge in the field of mycology. This study proposes a Swin Transformer-based approach to automate the identification process. The Swin Transformer model, known for its ability to capture complex spatial interactions, is adapted from ImageNet’s pre-trained model. The adaptation process is focused on fine-tuning the final classification layer to match the 5 classes of fungi present in the dataset. This classification layer is replaced by a new fully-connected layer that has the number of output according to the number of fungal classes. The weights on these layers are randomly initialized and trained in conjunction with several final convolutional layers. In addition, regularization techniques such as dropouts are applied to prevent overfitting. Adaptation using 5-fold cross-validation was carried out to find the best fold with hyperparameters including AdamW optimizer with a learning rate of 10−3, StepLR scheduler, batch size of 128 images, and a total of 9 epochs / iterations. After that, fine-tuning is carried out on the best fold with hyperparameters including AdamW optimizer with a learning rate of 10−5, StepLR scheduler, batch size of 32 images, and a total of 100 epochs / iterations. The final result showed excellent performance, with accuracy, precision, recall and an average F1-score of 95%. These results show the potential of the Swin Transformer in becoming an effective tool for mycologists. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Vision-Based Landing Guidance Through Tracking and Orientation Estimation

Vision-Based Landing Guidance Through Tracking and Orientati...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： João P. K. Ferreira João P. Pinto Júlia Moura Yi Li Cristiano L. Castro Plamen Angelov Graduate Program in Electrical Engineering Universidade Federal de Minas Gerais School of Computing and Communications Lancaster University

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Fixed-wing aerial vehicles are equipped with functional-ities such as ILS (instrument landing system), PAR (precision approach radar) and, DGPS (differential global positioning system), enabling fully automated landings. How-ever, these systems impose significant costs on airport op-erations due to high installation and maintenance requirements. Moreover, since these navigation parameters come from ground or satellite signals, they are vulnerable to in-terference. A more cost-effective and independent alternative for guiding landing is a vision-based system that de-tects the runway and aligns the aircraft, reducing the pi-lot's cognitive load. This paper proposes a novel frame-work that addresses three key challenges in developing au-tonomous vision-based landing systems. Firstly, to over-come the lack of aerial front-view video data, we created high-quality videos simulating landing approaches through the generator code available in the LARD (landing approach runway detection dataset) repository. Secondly, in contrast to former studies focusing on object detection for finding the runway, we chose the state-of-the-art model Lo-RAT to track runways within bounding boxes in each video frame. Thirdly, to align the aircraft with the designated landing runway, we extract runway keypoints from the re-sulting LoRAT frames and estimate the camera relative pose via the Perspective-n-Point algorithm. Our experimental re-sults over a dataset of generated videos and original images from the LARD dataset consistently demonstrate the proposed framework's highly accurate tracking and alignment capabilities. Our approach source code and the Lo-RAT model pre-trained with LARD videos are available at https://***/jpklock2/vision-based-landing-guidance

关键词： Visualization Codes Accuracy Atmospheric modeling Pose estimation Video sequences Radar tracking Generators Aircraft navigation Global Positioning System

来源：评论

学校读者我要写书评

暂无评论

An Energy-Efficient StEFCal VLSI Design with Approximate Squarer and Divider Units

An Energy-Efficient StEFCal VLSI Design with Approximate Squ...

引用

IEEE Latin American Symposium on Circuits and Systems (LASCAS)

作者： Morgana M. A. Da Rosa Patrícia Da Costa Guilherme Paim Eduardo Da Costa Rafael Soares Sergio Bampi Graduate Program on Computing Federal University of Pelotas (UFPel) Pelotas Brazil Graduate Program on Microelectronics Federal University of Rio Grande do Sul Porto Alegre Brazil Graduate Program on Electronic Engineering and Computing Catholic University of Pelotas Pelotas Brazil

Approximate computing attempts to maximize area and energy savings for a trade-off between quality and efficiency. This paper investigates the approximate squarer and divider units in the calibration procedure for radio astronomy called StEFCal (Statistically Efficient and Fast Calibration). The StEFCal circuit uses two squarer units from the literature, i.e., radix-4 (AxRSU) and SquASH, and iterative-based Newton-Raphson (NR) and Goldschmid (GLD) dividers. We demonstrate the efficiency of StEFCal using the approximate arithmetic operators from the Pareto-optimal that show the area- and power-quality trade-off. The results show that using the AxRSU combined with the NR divider improves the Mean Square Error (MSE) by 4.24%, with 58x more energy saving than the state-of-the-art.

关键词： Radio astronomy Circuits and systems Power quality Mean square error methods Very large scale integration Approximation algorithms Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Watermarking System Through Approximate Discrete Haar Wavelet Transform

Energy-Efficient Watermarking System Through Approximate Dis...

引用

IEEE International Conference on Electronics, Circuits and Systems (ICECS)

作者： Thiago Rutz Morgana Da Rosa Rodrigo Lopes Eduardo Da Costa Rafael Soares Sergio Bampi Graduate Program on Computing - Federal University of Pelotas (UFPel) Pelotas Brazil Graduate Program on Electronic Engineering and Computing - Catholic University of Pelotas (UCPel) Pelotas Brazil Federal University of Rio Grande do Sul (UFRGS) Porto Alegre Brazil

ISBN: (数字)9798350377200

ISBN: (纸本)9798350377217

This work introduces a low-energy-driven watermarking system that employs the approximate discrete Haar Wavelet transform (AxDHWT) to insert watermark images into host images. Our contribution involves developing an energy-efficient AxDHWT watermarking system in VLSI hardware. Additionally, we present a model implemented in MATLAB, incorporating probability theory for accuracy estimation, along with extensive testing conducted under diverse attack scenarios. Logic synthesis (LS) results show that the AxDHWT watermarking system demonstrates low power and reduces area cost, featuring ten fewer arithmetic circuits than the current state-of-the-art. Remarkably, our AxDHWT-based architecture showcases reductions of $1.33\times$ in area and $2.88\times$ in energy consumption compared to the state-of-the-art system.

关键词： Salt Transform coding Watermarking Transforms Very large scale integration Speckle Energy efficiency Discrete wavelet transforms Testing Arithmetic

来源：评论

学校读者我要写书评

暂无评论

Acceptance Analysis of IWB Systems in Education using UTAUT2 Model: The Moderating Role of Perceived Technological Innovations

Acceptance Analysis of IWB Systems in Education using UTAUT2...

引用

2023 IEEE International Conference on Automatic Control and Intelligent Systems, I2CACIS 2023

作者： De Jesus, Noelyn Castro, Eltimar T. Buyan, Cory Antonio Batangas State University College of Informatics & Computing Sciences Batangas Philippines Technological Institute of the Philippines Graduate Program Department Manila Philippines Ballard Power Systems Business Technology Burnaby Canada

ISBN: (纸本)9798350321302

Interactive Whiteboard (IWB) Systems are increasingly being used to replace traditional whiteboards in educational activities, making them more efficient and interesting for both teachers and students. However, no studies have been conducted to investigate how age, educational level, and employment status can impact the adoption and usage of IWB systems in the educational setting. The study aims to analyze the acceptance and the influencing factors on faculty members' intention and usage behavior towards IWB systems in teaching, utilizing the Modified-Unified Theory of Acceptance and Use of Technology 2 (UTAUT2) model. 135 faculty members from various colleges and departments across Batangas State University ARASOF-Nasugbu Campus were surveyed and data was analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM) through SmartPLS software for hypotheses testing. The results of the study indicate that faculty members' behavioral intention to use interactive whiteboard systems in teaching is positively influenced by performance expectancy and social influence. Moreover, facilitating conditions and habit positively impact usage behavior. This study, therefore, concludes that there is significant roles of performance expectancy and social influence as well as the moderating effect of age on the behavioral intention to use interactive whiteboard (IWB) systems in education. Furthermore, the study confirms that effort expectancy, hedonic motivation, and status as moderating variables significantly influence faculty members' usage behavior when using IWB systems in teaching. © 2023 IEEE.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Quality-Reconfigurable Approximate Multiplier Utilizing Select Leading One-Bit Blocks

Quality-Reconfigurable Approximate Multiplier Utilizing Sele...

引用

IEEE Latin American Symposium on Circuits and Systems (LASCAS)

作者： João M. Bedin Pedro T. L. Pereira Rodrigo N. Wuerdig Eduardo Da Costa Sergio Bampi Graduate Program in Microelectronics (PGMicro) - Federal University of Rio Grande do Sul (UFRGS) Porto Alegre Brazil Graduate Program in Electronic Engineering and Computing - Catholic University of Pelotas (UCPel) Pelotas Brazil

ISBN: (数字)9798331522124

ISBN: (纸本)9798331522131

Multipliers are essential for emerging technologies, as they are vital arithmetic circuits in many energy-efficient applications, such as digital signal processing and machine learning applications. Approximate multipliers (AxM) became an optimal option for applications in ASIC systems with error tolerance. This paper proposes to develop a run-time reconfigurable AxM with four approximation levels in a single circuit, evaluating accuracy and circuit metrics (e.g., circuit area, timing, and power consumption) based on the leading one-bit-based approximate (LoBA) multiplier. The results achieve a circuit area reduction of 52% less area and up to 27% less power consumption when compared with equivalent architecture based on LoBA state-of-art. Applying the proposed RLoBA to a normalized least mean square (NLMS) adaptive filter case study, we obtain 22.95% less power consumption using dynamic approximate level selection than the precise multiplier while maintaining the same accuracy level.

关键词： Measurement Power demand Accuracy Circuits Adaptive filters Machine learning Lead Timing Reconfigurable architectures Standards

来源：评论

学校读者我要写书评

暂无评论

Exploring Heterogeneous Open Multi-Agent Systems on Cloud Using a Docker-Based Architecture*

Exploring Heterogeneous Open Multi-Agent Systems on Cloud Us...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Gustavo Lameirão de Lima Marilton Sanchotene de Aguiar Graduate Program in Computing (PPGC) Federal University of Pelotas (UFPel) Pelotas Brazil

In Open Multi-Agent Systems (OMAS), heterogeneous agents in varying environments or models can transition from one system to another, retaining their attributes and knowledge. This migration process results in an augmented development complexity compared to conventional Multi-Agent Systems. Additionally, the intricacy of this transition arises from uncertainties and dynamic behaviors associated with the agents' changes, necessitating the formulation of techniques to analyze this complexity and comprehend the system's overall behavior. To address these challenges, we employed Docker, which enables a flexible architecture that accommodates different programming languages and frameworks for the agents. This paper introduces a Docker-based architecture that aids OMAS development, facilitating agent migration between various models operating in heterogeneous hardware and software setups. To validate the proposed approach, we conducted simulations using NetLogo's Open Sugarscape 2 Constant Growback and JaCaMo's Gold Miners. These simulations were executed locally, in the cloud, and in a hybrid mode to assess the feasibility of the proposed architecture.

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：