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

A New Design of CR-NOMA and Its Application to AoI Reduction

arXiv

引用

arXiv 2023年

作者： Ding, Zhiguo Dobre, Octavia A. Fan, Pingzhi Poor, H. Vincent Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi United Arab Emirates Department of Electrical and Electronic Engineering University of Manchester Manchester United Kingdom The Faculty of Engineering and Applied Science Memorial University St. John’sNLA1B 3X5 Canada The Institute of Information Coding & Transmission Key Lab of Sichuan Province Southwest Jiaotong University Chengdu China The Department of Electrical and Computer Engineering Princeton University PrincetonNJ08544 United States

The aim of this letter is to develop a new design of cognitive radio inspired non-orthogonal multiple access (CR-NOMA), which ensures that multiple new users can be supported without causing disruption to the legacy network. Analytical results are developed to characterize the statistical properties of the number of supported new users. The developed CR-NOMA scheme is compatible to various communication networks, because it can be implemented as a simple add-on. An example of using CR-NOMA as an add-on in time-division multiple access networks for age of information (AoI) reduction is illustrated, where analytical results are developed to demonstrate the superior performance gain of using CR-NOMA. Copyright © 2023, The Authors. All rights reserved.

关键词： Cognitive radio

来源：评论

学校读者我要写书评

暂无评论

Quantum compression with classically simulatable circuits

arXiv

引用

arXiv 2022年

作者： Anand, Abhinav Kottmann, Jakob S. Aspuru-Guzik, Alán Chemical Physics Theory Group Department of Chemistry University of Toronto Canada Department of Computer Science University of Toronto Canada Department of Chemical Engineering and Applied Chemistry University of Toronto Canada Department of Materials Science and Engineering University of Toronto Canada Vector Institute for Artificial Intelligence Toronto Canada Toronto Canada

As we continue to find applications where the currently available noisy devices exhibit an advantage over their classical counterparts, the efficient use of quantum resources is highly desirable. The notion of quantum autoencoders was proposed as a way for the compression of quantum information to reduce resource requirements. Here, we present a strategy to design quantum autoencoders using evolutionary algorithms for transforming quantum information into lower-dimensional representations. We successfully demonstrate the initial applications of the algorithm for compressing different families of quantum states. In particular, we point out that using a restricted gate set in the algorithm allows for efficient simulation of the generated circuits. This approach opens the possibility of using classical logic to find low representations of quantum data, using fewer computational resources. © 2022, CC BY.

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

Carbon-Aware Edge Computing for Internet of Everything Networks: A Digital Twin Approach

引用

IEEE Internet of Things Journal 2025年

作者： Huynh, Dang Van Khosravirad, Saeed R. Sharma, Vishal Kim, Joongheon Canberk, Berk Duong, Trung Q. Memorial University Faculty of Engineering and Applied Science St. John’sNLA1B 3X5 Canada Nokia Bell Labs Murray HillNJ07964 United States Queen’s University Belfast School of Electronics Electrical Engineering and Computer Science BelfastBT7 1NN United Kingdom Korea University Department of Electrical and Computer Engineering Seoul02841 Korea Republic of Engineering and The Built Environment at Edinburgh Napier University School of Computing EdinburghEH11 4BN United Kingdom

The rapid growth of edge computing has enabled low-latency and high-efficiency processing for a wide range of applications;however, it also leads to significant energy consumption and carbon emissions. In this context, this study investigates a CO2 emission minimisation problem in a digital twin-aided edge computing system, aiming to optimise task offloading decisions, transmit power, and processing rates of Internet of Things (IoT) devices. To address the formulated mixed-integer non-linear programming problem, we propose two solutions: an alternating optimisation method based on the successive convex approximation framework and a deep reinforcement learning (DRL) approach. Extensive simulations validate the effectiveness of the proposed solutions, demonstrating significant reductions in CO2 emissions, robust optimisation performance, and superior results compared to benchmark schemes. The findings highlight the feasibility of integrating advanced optimisation and artificial intelligence-driven techniques to achieve environmentally sustainable and high-performance edge computing systems, paving the way for greener technological innovation. © 2014 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A comparative literature review on extensive research on dynamic time warping and its variants for crop forecasting and vegetation using environmental parameters

TechRxiv

引用

TechRxiv 2023年

作者： Bediako-Kyeremeh, Bright Wornyo, Dickson Keddy Dashantha, Maheesha Pokuaa, Henrietta Adjei Badu, Benjamin Agyemang Agyemang, Sylvester Osibo, Benjamin Kwapong Ambitosoa, Lorenzo Mamelona Ye, Wenzheng Li, Jia Appau, Oppong Kofi Nanjing University of Information Science and Technology School of Electronic and Information Engineering Nanjing210044 China Nanjing University of Information Science and Technology School of Computer and Software Nanjing210044 China Sunyani Technical University Department of Computer Science Faculty of Applied Science Box 206 Sunyani Ghana University of Professional Studies Accra Department of Information & Communication Studies Box LG 149 Accra Ghana Sunyani Technical University Ghana

Dynamic Time warping (DTW) is a technique to estimate the best match between two common temporal sequences that are insensitive to synchronize well. This work looked to determine how DTW, and some common environmental parameters influence crop yield or vegetation. This was set out to identify literature using DTW and its variants in the direction of crop yield or vegetation. A total of 14 DTW and its variants and 10 environmental parameters that promoted crop yield or vegetation were adopted. Some DTW and its variants such as Time Weighted DTW, Derivative DTW, Weighted DTW, Vector DTW, Mahalanobis Distance DTW, Gaussian DTW, Open Locally Weighted DTW, and classical DTW recorded some 45 research works in their respective directions. Graphical DTW, Sparse DTW, Fast DTW, multiscale DTW, and Continuous DTW had no research about crop yield or vegetation in its direction. Environmental parameters such as wind speed and wind direction had no DTW and its variants modeled with them in crop yield or vegetation mapping, other environmental parameters recorded a total of 45 works in its direction. This points out gaps in DTW and its variants in crop yield and the concentration of variants and environmental parameters often used in crop yield and vegetation mapping. © 2023, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Leveraging both faces of polar semiconductor wafers for functional devices

arXiv

引用

arXiv 2024年

作者： van Deurzen, Len Kim, Eungkyun Pieczulewski, Naomi Zhang, Zexuan Feduniewicz-Zmuda, Anna Chlipala, Mikolaj Siekacz, Marcin Muller, David Xing, Huili Grace Jena, Debdeep Turski, Henryk School of Applied and Engineering Physics Cornell University IthacaNY14853 United States Department of Electrical and Computer Engineering Cornell University IthacaNY14853 United States Department of Materials Science and Engineering Cornell University IthacaNY14853 United States Institute of High Pressure Physics "Unipress" Polish Academy of Sciences Warsaw01-142 Poland Kavli Institute Cornell for Nanoscale Science Cornell University IthacaNY14853 United States

Unlike non-polar semiconductors such as silicon, the broken inversion symmetry of the wide bandgap semiconductor gallium nitride leads to a large electronic polarization along a unique crystal axis.1 This makes the two surfaces of the semiconductor wafer perpendicular to the polar axis dramatically different in their physical and chemical properties.2 In the last three decades, the cation (gallium) face of gallium nitride has been used for photonic devices such as LEDs and lasers.3–5 Though the cation face has also been predominantly used for electronic devices, the anion (nitrogen) face has recently shown promise for high electron mobility transistors due to favorable polarization discontinuities.6 In this work we introduce dualtronics, showing that it is possible to make photonic devices on the cation face, and electronic devices on the anion face, of the same semiconductor wafer. This opens the possibility for leveraging both faces of polar semiconductors in a single structure, where electronic, photonic, and acoustic properties can be implemented on opposite faces of the same wafer, dramatically enhancing the functional capabilities of this revolutionary semiconductor family. © 2024, CC BY-NC-ND.

关键词： High electron mobility transistors

来源：评论

学校读者我要写书评

暂无评论

Quantifiable resilience analytics of power grids by simulating power flows 30

Quantifiable resilience analytics of power grids by simulati...

引用

30th European Safety and Reliability Conference, ESREL 2020 and 15th Probabilistic Safety Assessment and Management Conference, PSAM 2020

作者： Hupp, Daniel Hruz, Tomas Mock, Ralf School of Engineering Zurich University of Applied Sciences Switzerland Department of Computer Science ETH Zurich Switzerland

ISBN: (纸本)9789811485930

New challenges are expected to emerge for the operation of power grids and associated power flows from the growing use of renewable energies and the increasing demand of electricity due to the electrification of mobility. Current stability considerations of power grid under normal operating conditions are presumably insufficient to handle contingencies. For this, the concept of resilience analysis offers advantages to study the operation under the influence of disturbances. However, there is still a lack of suitable approaches. This includes a lack of metrics for making quantitative statements about the grid resilience. This paper develops a qualitative concept of power grid resilience and complements it by a quantitative analysis method, which uses the modeling and simulation of power flows. This concept is illustrated by a case study. So, this paper makes a contribution to provide a suitable approach and a quantitative metric for power grid resilience. Copyright © ESREL2020-PSAM15 Organizers.

关键词： Electric load flow

来源：评论

学校读者我要写书评

暂无评论

Flexible-type Ultrathin Holographic Endoscope for Microscopic Imaging of Unstained Biological Tissues

Flexible-type Ultrathin Holographic Endoscope for Microscopi...

引用

Imaging Systems and Applications, ISA 2022

作者： Kang, Munkyu Choi, Wonjun Hong, Jin Hee Katz, Ori Lee, Byunghak Kim, Guang Hoon Choi, Youngwoon Choi, Wonshik Seoul02481 Korea Republic of Department of Physics Korea University Seoul02481 Korea Republic of Department of Applied Physics The Selim and Rachel Benin School of Computer Science & Engineering The Hebrew University of Jerusalem Jerusalem9190401 Israel Korea Electrotechnology Research Institute Ansan15588 Korea Republic of B2LAB Co. Ltd. 37673 Korea Republic of Department of Bioengineering Korea University Seoul02481 Korea Republic of

We present a fully flexible and ultrathin lensless fiber endoscope that can perform high-resolution holographic imaging of unstained tissues through a narrow and curved passage. A unique algorithm is developed for cal... 详细信息

ISBN: (纸本)9781557528209

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

Segmentation of Nuclei in Histopathology images using Fully Convolutional Deep Neural Architecture

Segmentation of Nuclei in Histopathology images using Fully ...

引用

2020 International Conference on Computing and Information Technology, ICCIT 2020

作者： Natarajan, V. Anantha Sunil Kumar, M. Patan, Rizwan Kallam, Suresh Noor Mohamed, Mohamed Yasin Sree Vidyanikethan Engineering College Department of Computer Science and Engineering Tirupati India Velagapudi Ramakrishna Siddhartha Engineering College Department of Computer Science and Engineering Vijayawada India Sultan Qaboos University Center for Preparatory Studies Department of Math and IT Muscat Oman

ISBN: (纸本)9781728126807

Nuclei segmentation is an initial step in the automated analysis of digitized microscopic images. This paper focuses on utilizing the LinkNET-34 architecture for semantic segmentation of nuclei from the HE stained breast cancer histopathology images. The segmentation process is implemented in two stages where in the first stage the HE stained images are pre-processed to reduce the variance caused because of staining the microscopic images and scanning the slides. During the second stage the preprocessed images are given as input to the LinkNET network which consists of both down-sampling and up-sampling layers. The network is trained using a set of WSI patches released during the Data science bowl 2018 competition. The performance of the deep learning model is evaluated based on the segmentation accuracy measured using the Dice Coefficient. © 2020 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

An Application-Aware Clustering Strategy in Vehicular Ad Hoc Network

An Application-Aware Clustering Strategy in Vehicular Ad Hoc...

引用

International Conference on Computing, Electronics & Communications engineering (iCCECE)

作者： Chi-Hung Wei Chin-Chih Chang Chien-Hao Chu Sean Hsiao Ph.D. Program in Engineering Science Chung Hua University Hsinchu City Taiwan Department of Computer Science and Information Engineering Chung Hua University Hsinchu City Taiwan Bachelor Program in Applied Foreign Language and Smart Commerce Chung Hua University Hsinchu City Taiwan

VANET (Vehicular Ad Hoc Network) was developed to address the unique challenges of communication in a mobile vehicular environment. This technology can enhance driving safety and traffic control. Moreover, similar principles can be applied to unmanned aerial vehicles and robotics. When transmitting data in moving vehicles, it is challenging as access points and base stations keep changing, requiring handovers between different access points and base stations. Clustering is a popular approach used to address this challenge. Common clustering strategies are based on the proximity, communication range, the density, the application requirements of the moving vehicles, or hybrid of them. In this paper, we propose a clustering strategy based on the application sublayer in the vehicle communication protocol. If two computing devices on the move run the same application, they can be grouped together. The contribution of this research is to develop a clustering mechanism based on the application with very low overhead. We also validate the proposed method through simulations. The simulation results indicate that the proposed method is feasible.

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：