检索结果-内蒙古大学图书馆

The Journal of Machine Learning Research 2024年第1期25卷 2557-2625页

作者： Chanwoo Park Ernest K. Ryu Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Massachusetts Department of Mathematical Sciences Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea

In this work, we present a novel algorithm design methodology that finds the optimal algorithm as a function of inequalities. Specifically, we restrict convergence analyses of algorithms to use a prespecified subset of inequalities, rather than utilizing all true inequalities, and find the optimal algorithm subject to this restriction. This methodology allows us to design algorithms with certain desired characteristics. As concrete demonstrations of this methodology, we find new state-of-the-art accelerated first-order gradient methods using randomized coordinate updates and backtracking line searches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Gain Enhancement of Antenna-on-Chip at 94 GHz with an Integrated Artificial Magnetic Conductor for 6G System-on-Chip

Gain Enhancement of Antenna-on-Chip at 94 GHz with an Integr...

引用

IFIP International Conference on Very Large Scale Integration (VLSI-SoC)

作者： Yiyang Yu Atif Shamim Electrical and Computer Engineering Program King Abdullah University of Science and Technology Thuwal Saudi Arabia

Silicon-based complementary metal oxide semiconductor (CMOS) process has become one of the most popular processes to realize system-on-chip (SoC). However, as one of the essential components of wireless SoC, antennas are typically suffering from the poor radiation because of the highly conductive silicon substrate. Such antennas are known as antenna-on-chip (AoC). To enhance the radiation performance of AoC, artificial magnetic conductors (AMC) with double periodic strip structure layers has been proposed in this paper that can not only provide in-phase reflection but also isolate the antenna from the lossy silicon substrate. The proposed AMC shows a gain enhancement of 4.5 dB. The AMC-backed AoC is well-matched within 77-125 GHz and provides a boresight gain of 2 dBi at 94 GHz.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Dual-band electrically Small Quasi-isotropic Antenna

A Novel Dual-band Electrically Small Quasi-isotropic Antenna

引用

European Conference on Antennas and Propagation, EuCAP

作者： Hanguang Liao Atif Shamim Electrical and Computer Engineering Program King Abdullah University of Science and Technology Thuwal Saudi Arabia

Quasi-isotropic antennas have gained attention due to the emergence of the Internet of Things (IoT) and Wireless Sensing Networks (WSNs), for their orientation-insensitive communication ability. For those applications, electrically small (ES) antennas are usually preferred, which can save space for the IoT or sensing nodes, while reducing the material cost. Several compact isotropic antennas have been reported recently. However, only very few of them have shown dual-band operation ability. A novel design method to design a dual-band quasi-isotropic ES antenna is presented in this conference proceeding. The utilization of a band stop filter (BSF) enables the conventional single-band quasi-isotropic split ring resonator (SRR) antenna to behave in a dual-band operation, while maintaining the quasi-isotropic radiation for both bands. The proposed antenna is designed, fabricated, and measured, which shows a dual-band operation (both bands in ka<1 region) while maintaining decent performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Classification and Prediction of Knee Osteoarthritis by Deep Learning Approach 3rd

Classification and Prediction of Knee Osteoarthritis by Deep...

引用

3rd International Conference on Intelligent Computing Techniques for Smart Energy Systems, ICTSES 2023

作者： Saraswat, Amit Tooley, Tanya Shrivastav, Snigdha Srivastava, Devesh Kumar Department of Electrical Engineering Manipal University Rajasthan Jaipur303007 India Senior Analyst EY Haryana Gurgaon India Master of Science in Data Science program at the University of Rochester New York United States Department of Information Technology Manipal University Rajasthan Jaipur303007 India

ISBN: (纸本)9789819784288

The purpose of this research work on medical image analysis is to identify and diagnose knee osteoarthritis (OA) utilizing medical images by applying machine learning techniques. Knee OA is a degenerative joint disease that is becoming more prevalent in aged people worldwide. The study examines the effectiveness of several machine learning algorithms, including deep learning, to analyze medical images of knee OA, such as X-rays and magnetic resonance imaging (MRI). The research findings suggest that using machine learning algorithms might greatly improve the accuracy and efficacy of detecting knee OA, especially in its early stages. Moreover, machine learning algorithms can assist in the creation of specialized treatment plans by predicting the progression of the disease and recommending appropriate remedies. The findings of this study show how machine learning-based medical image analysis has the potential to enhance patient outcomes and quality of life for those with knee OA. Cancer detection diagnosis, neurological condition identification, and cardiovascular function analysis are a few instances of medical picture analysis employing machine learning. Moreover, image-guided treatments have been made more accurate and surgical planning has been made easier with the use of machine learning algorithms. Various methods are applied to achieve a test accuracy of 76.10% which is just 5% less than the accuracy provided by the Kellen-Lawrence Grading Scale. Overall, machine learning-based medical image analysis has the potential to revolutionize medical practice by facilitating earlier and more precise diagnosis, individualized treatment planning, and improved patient outcomes. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Development of Perching and Fail-Safe Module for Wall Climbing Multi-copter 10th

Development of Perching and Fail-Safe Module for Wall Cli...

引用

10th International Conference on Robot Intelligence technology and Applications, RiTA 2022

作者： Kim, Taewan Tirtawardhana, Christian Yu, Byeongho Nahrendra, I. Made Aswin Kim, Seoktae Myung, Hyun Robotics Program Korea Advanced Institute of Science and Technology Daejeon34141 Korea Republic of School of Electrical Engineering Korea Advanced Institute of Science and Technology Daejeon34141 Korea Republic of KEPCO RI Korea Electric Power Corporation Daejeon34056 Korea Republic of

ISBN: (纸本)9783031268885

In recent years, various researches using UAVs (Unmanned Aerial Vehicles), especially multi-copter in various tasks, have been conducted due to their high mobility. Various perching mechanisms to perch the multi-copter onto the surface were developed for energy efficiency and to ensure safety while doing its tasks. However, developing mechanisms for multi-copter has limitations, such as limited payload. In this paper, we propose the perching and fail-safe module for the wall-climbing aerial robot "CAROS-Q" which can tilt its pose to perch on tilted surfaces. The proposed module consists of a passive perching mechanism with a specially designed suction cup to perch onto the surface safely, and a fail-safe mechanism to prevent falling from unexpected accidents. The prototype verifies the performance of the proposed module. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Operational Efficiency of Synchronous Reluctance Generator Systems using Vector Control

Operational Efficiency of Synchronous Reluctance Generator S...

引用

International electrical engineering Congress (iEECON)

作者： Ryunosuke Hayashi Wataru Kitagawa Takaharu Takeshita Azusa Takahashi Tatsuya Higashi Creative Engineering Education Program Nagoya Institute of Technology Nagoya Japan Department of Electrical and Mechanical Engineering Nagoya Institute of Technology Nagoya Japan Departmnt of Electrical and Mechanical Engineering Nagoya Institute of Technology Nagoya Japan Mobility Development Group DAIHATSU MOTOR CO. LTD. Osaka Japan

ISBN: (数字)9798331543952

ISBN: (纸本)9798331543969

This study aims to verify the operation of a system that combines a generator, an inverter to control it, and a power conditioner, as well as to observe the system efficiency at the theoretical MTPA (Maximum Torque Per Ampere) point. The generator is driven by vector control with a rated output of 12 kW, and the inverter has a capacity of 47 kW.

关键词： electrical engineering Torque Inverters Generators Reluctance generators

来源：评论

学校读者我要写书评

暂无评论

Predicting Microsatellite Instability from Histology Images with Dilated Neighborhood Attention Transformer in Colorectal Cancer 24

Predicting Microsatellite Instability from Histology Images ...

引用

24th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2024

作者： Chen, Yun-Chi Chao, Tung Phandita, Wimaya Nitya Sun, Tzu-Yu Wang, Huai-Zhi Hsieh, Yi-Hsien Hsu, Le-Yin Lin, Che Taipei Taiwan College of Bioresources and Agriculture NTU Taipei Taiwan National Taiwan University of Science and Technology Department of Computer Science and Information Engineering Taipei Taiwan Graduate Institute of Communication Engineering NTU Taipei Taiwan NTU Data Science Degree Program Taipei Taiwan NTU Department of Electrical Engineering Taipei Taiwan Center for Advanced Computing and Imaging in Biomedicine NTU Taipei Taiwan NTU Smart Medicine and Health Informatics Program Taipei Taiwan

ISBN: (纸本)9798331518622

Microsatellite instability (MSI) is a pivotal genetic marker influencing the efficacy of immunotherapy in colorectal cancer. Traditional MSI examination often requires additional genetic or immunohistochemical tests, whereas histology images, widely available in colorectal cancer diagnosis, offer a valuable alternative for MSI prediction. Although Transformer-based models have demonstrated promising outcomes in predicting MSI from histology images, they are hampered by traditional local attention mechanisms that struggle to capture long-range interdependencies and establish a comprehensive global receptive field. In this study, we introduce DiNAT-MSI, a novel framework for histology-based MSI prediction that incorporates the Dilated Neighborhood Attention Transformer (DiNAT). This model enhances global context recognition and substantially expands receptive fields, all without additional computational burden. Our results demonstrate that DiNAT-MSI achieves a superior patientwise AUROC compared to ResNet18 and Swin Transformer, along with commendable explainability. Our work not only illustrates a more accessible diagnostic tool for leveraging histological data but also underscores the potential of Transformerbased models with sophisticated attention designs in advancing precision medicine for colorectal cancer patients. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

TreeXGNN: can gradient-boosted decision trees help boost heterogeneous graph neural networks? 48

TreeXGNN: can gradient-boosted decision trees help boost het...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Hong, Ming-Yi Chang, Shih-Yen Hsu, Hao-Wei Huang, Yi-Hsiang Wang, Chih-Yu Lin, Che Academia Sinica Research Center for Information Technology Innovation Taiwan National Taiwan University and Academia Sinica Graduate Program of Data Science Taiwan National Taiwan University Graduate Institute of Communication Engineering Taiwan National Taiwan University Department of Electrical Engineering Taiwan

ISBN: (纸本)9781728163277

Graph neural networks are a promising deep learning method that can apply graph structures to various tasks. In real-world scenarios, we often have heterogeneous graphs, wherein different node and edge types capture complex interactions between nodes. High-dimensional node features provide rich information about the target nodes. Conventional heterogeneous graph neural networks (HGNN) focus more on graph structures than node features and may have difficulties extracting knowledge from complex node features. In this study, we propose a novel framework, the tree-boosted heterogeneous graph neural network abbreviated as TreeXGNN, which could efficiently and automatically extract target node features via gradient-boosted decision trees (GBDT). It integrates community structure information with proper fusion modules and a shared feature space design on HGNN. We achieved state-of-the-art performance on the three well-known heterogeneous graph benchmark datasets, IMDB, DBLP, and ACM, and significantly improved performance compared to previous studies. Our work paves the foundation for integrating tree-based models to boost HGNNs for general community analysis. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient In-memory Computing Hardware for Quantized Neural Networks: State-of-the-art, Open Challenges and Perspectives

arXiv

引用

arXiv 2023年

作者： Krestinskaya, Olga Zhang, Li Salama, Khaled Nabil Electrical and Computer Engineering Program the Division of Computer Electrical and Mathematical Sciences and Engineering King Abdullah University of Science and Technology Thuwal23955 Saudi Arabia

The amount of data processed in the cloud, the development of Internet-of-Things (IoT) applications, and growing data privacy concerns force the transition from cloud-based to edge-based processing. Limited energy and computational resources on edge push the transition from traditional von Neumann architectures to In-memory Computing (IMC), especially for machine learning and neural network applications. Network compression techniques are applied to implement a neural network on limited hardware resources. Quantization is one of the most efficient network compression techniques allowing to reduce the memory footprint, latency, and energy consumption. This paper provides a comprehensive review of IMC-based Quantized Neural Networks (QNN) and links software-based quantization approaches to IMC hardware implementation. Moreover, open challenges, QNN design requirements, recommendations, and perspectives along with an IMC-based QNN hardware roadmap are provided. © 2023, CC BY.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Development of LED Lighting for Microalgae Propagation with Emission Spectrum Having Broader Emission Peaks

Development of LED Lighting for Microalgae Propagation with ...

引用

Sustainable Smart Lighting World Conference & Expo (LS18), IEEE

作者： Nobuaki Hosoda Takashi Murata Takayuki Misu Graduate School of Engineering Master's Degree Program in Electrical and Electronic Engineering Kanagawa Institute of Technology Atsugi Kanagawa Japan Department of Applied Chemistry and Bioscience Faculty of Engineering Kanagawa Institute of Technology Atsugi Kanagawa Japan Department of Electrical and Electronic Engineering Faculty of Engineering Kanagawa Institute of Technology Atsugi Kanagawa Japan

ISBN: (数字)9798331540197

ISBN: (纸本)9798331540203

In this study, we aimed to develop LED lighting with an emission spectrum effective for microalgae propagation, and fabricated LED lighting with Phosphor layer RGB, which has peaks in the red, green, and blue wavelength bands, and Phosphor layer RG’B’, which has broader peaks in the red, green, and blue wavelength bands. In order to examine the effect of microalgae propagation, Closterium ehrenbergii samples prepared at different dilution rates were irradiated with LED illumination light of Phosphor layer RG’B’ and Phosphor layer RGB, respectively, for 7 days, and their propagation rates were compared. The results of the experiment showed that Phosphor layer RG’B’ produced a higher propagation rate than Phosphor layer RGB.

关键词： Phosphors Lighting Light emitting diodes

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：