检索结果-内蒙古大学图书馆

Large circuit models: opportunities and challenges

Science China(Information Sciences) 2024年第10期67卷 25-66页

作者： Lei CHEN Yiqi CHEN Zhufei CHU Wenji FANG Tsung-Yi HO Ru HUANG Yu HUANG Sadaf KHAN Min LI Xingquan LI Yu LI Yun LIANG Jinwei LIU Yi LIU Yibo LIN Guojie LUO Hongyang PAN Zhengyuan SHI Guangyu SUN Dimitrios TSARAS Runsheng WANG Ziyi WANG Xinming WEI Zhiyao XIE Qiang XU Chenhao XUE Junchi YAN Jun YANG Bei YU Mingxuan YUAN Evangeline F.Y.YOUNG Xuan ZENG Haoyi ZHANG Zuodong ZHANG Yuxiang ZHAO Hui-Ling ZHEN Ziyang ZHENG Binwu ZHU Keren ZHU Sunan ZOU Huawei Noah’s Ark Lab School of Integrated Circuits Peking University Faculty of Electrical Engineering and Computer Science Ningbo University Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Department of Computer Science and Engineering The Chinese University of Hong Kong School of Integrated Circuits Southeast University Huawei HiSilicon Peng Cheng Laboratory School of Computer Science Peking University School of Microelectronics State Key Laboratory of Integrated Chips and System Fudan University School of Artificial Intelligence Shanghai Jiao Tong University

Within the electronic design automation(EDA) domain, artificial intelligence(AI)-driven solutions have emerged as formidable tools, yet they typically augment rather than redefine existing methodologies. These solutions often repurpose deep learning models from other domains, such as vision, text, and graph analytics, applying them to circuit design without tailoring to the unique complexities of electronic circuits. Such an “AI4EDA” approach falls short of achieving a holistic design synthesis and understanding,overlooking the intricate interplay of electrical, logical, and physical facets of circuit data. This study argues for a paradigm shift from AI4EDA towards AI-rooted EDA from the ground up, integrating AI at the core of the design process. Pivotal to this vision is the development of a multimodal circuit representation learning technique, poised to provide a comprehensive understanding by harmonizing and extracting insights from varied data sources, such as functional specifications, register-transfer level(RTL) designs, circuit netlists,and physical layouts. We champion the creation of large circuit models(LCMs) that are inherently multimodal, crafted to decode and express the rich semantics and structures of circuit data, thus fostering more resilient, efficient, and inventive design methodologies. Embracing this AI-rooted philosophy, we foresee a trajectory that transcends the current innovation plateau in EDA, igniting a profound “shift-left” in electronic design methodology. The envisioned advancements herald not just an evolution of existing EDA tools but a revolution, giving rise to novel instruments of design-tools that promise to radically enhance design productivity and inaugurate a new epoch where the optimization of circuit performance, power, and area(PPA) is achieved not incrementally, but through leaps that redefine the benchmarks of electronic systems' capabilities.

关键词： AI-rooted EDA large circuit models (LCMs) multimodal circuit representation learning circuit optimization

来源：评论

学校读者我要写书评

暂无评论

Fine-grained Energy-efficient Data Center Traffic Scheduling Mechanism Based on Hierarchical Control

Journal of Network Intelligence

引用

Journal of Network Intelligence 2023年第3期8卷 742-757页

作者： Niu, Tianyu Li, Honghui Li, Weidong Por, Lip Yee College of Computer and Information Engineering Inner Mongolia Agricultural University Inner Mongolia Hohhot China Department of Computer System and Technology Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur50603 Malaysia

With the continuous expansion of the data center, its energy consumption is also increasing. Aiming at the problem that the high redundancy of modern data center network causes low energy-consumption utilization, this paper proposes an energy-saving traffic scheduling algorithm (IMV-MLF) based on improved multi-layer-virtual-topology combined with maximum link-utilization path priority, which realizes more fine-grained control of each layer of virtual topology in data center network. Firstly, the relevant shap-ing linear programming mathematical model is established according to the optimization goal of energy conservation, which can minimize the energy consumption of the whole network as far as possible under the premise of meeting all network-flow requirements;Then, according to the optimization goal, the existing SDN based energy saving multi-layer-virtual-topology (EMV-SDN) method is improved. Whether the network devices in other layers are enabled is determined by the overall traffic level rather than the traffic level of a single link. On the basis of the opened level, the newly arrived network flows are preferentially allocated to the path with the highest link utilization, and overload link set is introduced, we can effectively use the available link routes with sufficient residual bandwidth to reduce congestion when the topology changes by marking the links whose link utilization reaches the critical value, and further count and close the links and switches which no network flows pass through. The experimental results show that the performance of IMV-MLF algorithm is better than multi-layer virtual topology energy saving (EMV-SDN) algorithm and the equivalent multipath (ECMP) algorithm in saving network energy. This result is helpful to provide another new idea for energy conservation of data center. © 2023, Journal of Network Intelligence.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

A Scalable Solution for Pneumonia Diagnosis: Transfer Learning for Chest X-ray Analysis 7

A Scalable Solution for Pneumonia Diagnosis: Transfer Learni...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Haque, Rezaul Sultana, Shayma Prasad, Chandan Hasan, Sayed Fardin, Hasib Sakib, Abdullah Al Malik, Neeru Kaushik, Keshav East West University Department of Cse Dhaka Bangladesh International American University Department of Management Information System United States Pimpri Chinchwad University Department of Computer Science and Engineering Maharashtra Pune India Westcliff University Department of Engineering Management United States Westcliff University Department of Information Technology United States Pimpri Chinchwad University School of Engineering & Technology Maharashtra Pune India Amity University Amity School of Engineering and Technology Punjab India

ISBN: (纸本)9798350350067

The high death rate and rapid spread of pneumonia make it a serious global health concern. The precision of traditional diagnostic techniques is often compromised, particularly in resource-limited settings. Existing studies have predominantly focused on either binary or multi-class classification, often relying on limited datasets, which affects the generalizability and robustness of models. Additionally, the interpretability and transparency of deep learning models remain challenging in clinical environments. Addressing these challenges is crucial for advancing diagnostic methodologies to combat pneumonia. This study explores the use of transfer learning to improve the reliability of pneumonia classification using chest X-ray images. An automated classification system was developed, utilizing a combination of image preprocessing techniques, feature extraction with GLRLM, and various machine learning and transfer learning algorithms. Two datasets were employed: the GWCMCx dataset with 5856 chest X-rays and another dataset comprising 9207 chest X-rays. The system was designed for both binary and multi-class classification scenarios. CapsuleNet emerged as the most effective model, achieving an accuracy of 99.02% in binary classification and 90.43% in multi-class classification, significantly outperforming previous studies. Additionally, a user-friendly web application was developed to facilitate the integration of the classification system into clinical workflows, accelerating clinical decision-making. This study demonstrates the potential of transfer learning to automate and improve pneumonia diagnosis, offering a scalable solution that can alleviate radiologists' workload and improve patient outcomes. © 2024 IEEE.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Magnetic-Inertial Odometry Design Using Artificial AC Magnetic Fields in Outdoor Environment

Magnetic-Inertial Odometry Design Using Artificial AC Magnet...

引用

2024 IEEE International Conference on Multisensor Fusion and Integration for Intelligent systems, MFI 2024

作者： Kwon, Dongha Seo, Juyoung Lee, Byungjin Sung, Sangkyung Konkuk Univ. Department of Aerospace Information System Engineering Korea Republic of Konkuk Univ. Academy of Applied Science and Technology Korea Republic of Konkuk Univ. Department of Mechanical and Aerospace Engineering Korea Republic of

ISBN: (纸本)9798350368031

Magnetic field vector measurement model derived from a simple geometric coil model has been widely reported. These field vector measurements can be used to estimate the pose of a vehicle at a high level of accuracy in real-time. In our previous work, we introduced a magnetic positioning system (MPS) using these magnetic field vector measurements and performed 2D pose estimation. In this paper, we first introduce the initial calibration of the magnetic field considering both the magnetic field measurements and theoretical models. Then, estimation of position, velocity, and attitude is performed by multi sensor fusion between calibrated MPS, odometer and INS. This is implemented in a tightly-coupled(TC) extended Kalman filter(EKF) structure. The results demonstrated precise three- dimensional navigation performance and the benefits of the tightly coupled structure, resulting in accurate navigation and robustness. © 2024 IEEE.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Voltage Improvement and Loss Reduction by Placement and Sizing of DG Using Grid Oriented Multi objective Particle Swarm Optimization 2

Voltage Improvement and Loss Reduction by Placement and Sizi...

引用

2nd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2023

作者： Agarwal, Vinay Agarwal, Sunil Mahela, Om Prakash Apex Institute of Engineering and Technology Department of Electrical Engineering Jaipur India Rvpn Power System Planning Division India Universidad Internacional Iberoamericana Erig Mexico

ISBN: (纸本)9798350347456

The paper designed a method using grid oriented multi-objective particle swarm optimization (GOMPSO) for optimally placing and sizes the distributed generators (DG) to achieve objective of reduction in the loss of active and reactive power and improvement in voltage on a radial feeder. Multi- objective function is formulated considering constraints of voltage deviations and loss of active as well as reactive powers. This objective function is optimized by optimal deployment of the DG units using particle swarm optimization. Study is performed without considering the DGs, considering one DG, two DGs, three DGs and four DGs. Active power loss reduction index (APLRI), reactive power loss reduction index (QLRI), and total voltage deviation index (TVDI) are designed to assess performance of the proposed method. This is also established that performance of designed GOMPSO technique is better relative to genetic algorithm (GA) based method for DG unit placement. MATLAB software is used perform study on IEEE- 33 bus distribution feeder. © 2023 IEEE.

关键词： Reactive power

来源：评论

学校读者我要写书评

暂无评论

Analysis of Regenerative Braking Energy Utilization in KfW i9000 Electric Trains on the Palur-Yogyakarta Operation 7

Analysis of Regenerative Braking Energy Utilization in KfW i...

引用

7th Astechnova International Energy Conference, ASTECHNOVA 2023

作者： Darmawan, Arief Budiarto, Rachmawan Irnawan, Roni Master Program System Engineering Faculty of Engineering Universitas Gadjah Mada Jl. Teknika utara no 3 Yogyakarta55281 Indonesia Department of Nuclear Engineering and Engineering Physics Faculty of Engineering Universitas Gadjah Mada Jl. Grafika 2 Yogyakarta55281 Indonesia Department of Electrical Engineering and Information Technology Faculty of Engineering Universitas Gadjah Mada Jl. Grafika 2 Yogyakarta55281 Indonesia

This study explores the potential assessment. of regenerative braking energy in the operation of Electric Multiple Units (EMU) on the Yogyakarta-Palur railway line, a 65.03 km. Prompted by a noticeable increase in passenger numbers in the Yogyakarta metropolitan buffer zone, the study calls for future energy management strategies, involving regenerative braking to reduce energy consumption. Utilizing a mathematical model implemented via MATLAB Simulink, the research encompasses complex train movement scenarios, considering variables such as acceleration values of 0.558 m/s2 and 1 m/s2, and deceleration values of -0.555 m/s2 and 0.36 m/s2. Speed limitations, travel patterns, and energy profiles are rigorously examined, along with incline influences, such as tangent angles of 0.0032 degrees and 0.0017 degrees. In segments like Purwosari-Solo Jebres, electrical energy consumption is quantified at 23.02 kWh, with regenerative braking energy at 1.42 kWh;in Maguwo-Brambanan, consumption is 15.28 kWh, with regenerative energy at 2.42 kWh. The peak power requirements and regenerative braking potentials were also determined, with values such as 619.9 kW and 225.7 kW, and 1785 kW and 198.2 kW respectively. The total electrical consumption for the routes from Palur to Yogyakarta and vice versa was found to be 325.52 kWh and 276.73 kWh, with energy recovery of 31.43 kWh and 26.6 kWh, and average energy recovery ratios of 9.66% and 9.61%. © Published under licence by IOP Publishing Ltd.

关键词： Railroads

来源：评论

学校读者我要写书评

暂无评论

Real-Time 4-Mode MDM Transmission Using Commercial 400G OTN Transceivers and All-Fiber Mode Multiplexers

引用

ZTE Communications 2024年第1期22卷 106-110页

作者： REN Fang LI Yidan YE Bing LIU Jianguo CHEN Weizhang School of Computer and Communication Engineering University of Science and Technology BeijingBeijing 100083China Department of WDM System Design ZTE CorporationBeijing 100029China

Weakly-coupled mode division multiplexing(MDM)technique is considered a promising candidate to enhance the capacity of an optical transmission system,in which mode multiplexers/demultiplexers(MMUX/MDEMUX)with low insertion loss and modal crosstalk are the key *** this paper,a low-modal-crosstalk 4-mode MMUX/MDEMUX for the weakly-coupled triple-ring-core few-mode fiber(TRC-FMF)is designed and fabricated with side-polishing *** measurement results show that a pair of MMUX/MDEMUX and 25 km weakly-coupled TRC-FMF MDM link achieve low modal crosstalk of lower than−17.5 dB and insertion loss of lower than 11.56 dB for all the four *** on the TRC-FMF and all-fiber MMUX/MDEMUX,an experiment for 25 km real-time 4-mode 3-λwavelength division multiplexing(WDM)-MDM transmission is conducted using commercial 400G optical transport network(OTN)*** experimental results prove weakly-coupled MDM techniques facilitate a smooth upgrade of the optical transmission system.

关键词： optical fiber couplers mode(de)multiplexers mode division multiplexing transmission

来源：评论

学校读者我要写书评

暂无评论

A Novel and Accurate Method of Diagnosis via AI and ML for Smart HC system 4

A Novel and Accurate Method of Diagnosis via AI and ML for S...

引用

4th IEEE International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2024

作者： Elizabeth, J. Ruby Emmanuel, Mathews Aswini, E. Pathak, Shriram Bhuvaneswari, M. Choubey, Abhishek Nehru Institute of Engineering and Technology Department of Computer Science and Business System Tamil Nadu T.M.Palayam India Sathyabhama University of Science and Technology chennai India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electronics and Communication Engineering India Ies Insititute of Technology and Management Ies University Department of Mechanical Engineering M.P. Bhopal India Karpagam Academy of Higher Education Department of Biomedical Engineering Coimbatore India Sreenidhi Institute of Science and Technology ghatkesar Hyderabad Yamnampet India

ISBN: (纸本)9798350360165

Recent breakthroughs in the internet of Issues (IoT), computing through the cloud, and the use of AI have changed the standard healthcare system, making a case for smart health care. By combining key technologies including IoT and AI, there is a major improvement in medical services. The merging of IoT and AI offers multiple possibilities within the healthcare industry. This study piece presents a new artificial intelligence- and internet of things convergence-based framework for disease detection in smart health care systems, emphasizing especially on cardiovascular diseases and diabetes. The suggested model includes separate steps, including data collection, preparation, classification, and parameter modification. Utilizing Internet of Things devices like smartwatches along with sensors enables smooth collection of information, while AI methods harness this data for the detection of illnesses. The technique presents a new approach, applying to the Crowd Search Optimizer algorithm-based Flowed Long and Short-Term Memory (CSO-CLSTM) approach to disease detection. CSO is applied to improve both 'weights' while 'bias' factors of the CLSTM framework, while the isolation Fg (iForest) method is implemented to remove outliers. Through testing with health care information, the CSO-LSTM model got excellent accuracy ratings of 96.16% when 97.26% in identifying heart disease while diabetes, respectively. Consequently, the suggested CSO-LSTM model appears as a solid and reliable method of disease evaluation in digital healthcare systems, showing its potential for broad application. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Algorithmic Trading Model for Stock Price Forecasting Integrating Forester with Golden Ratio Strategy 12

Algorithmic Trading Model for Stock Price Forecasting Integr...

引用

12th IEEE Region 10 Humanitarian technology Conference, R10-HTC 2024

作者： Govindan, Niranjana Baskaran, Bharathi Azizan, Azizul Yakub, Fitri Dhamanti, Inge Dhaya, C. SRMIST Faculty of Engineering & Technology Department of Computing Technologies Kattankulathur Chennai India Faculty of Intelligence Kuala Lumpur Malaysia Malaysia-Japan International Institute of Technology UTM Electronic System Engineering Department Kuala Lumpur Malaysia Universitas Airlangga Faculty of Public Health Department of Health Policy and Administration Surabaya Indonesia Adhiparasakthi Engineering College Department of Computer Science and Technology Melmaruvathur India

ISBN: (纸本)9798350340204

Algorithmic trading has emerged as a powerful tool for making data-driven trading decisions in financial markets. In this paper, we present an innovative algorithmic trading model for stock price forecasting that integrates forest-based machine learning algorithms with the Golden Ratio strategy. Our proposed approach aims to leverage the predictive power of machine learning while incorporating insights from technical analysis to enhance trading performance and profitability. The methodology involves data collection and preprocessing, feature engineering, model development, and performance evaluation. Historical stock price data, financial indicators, and sentiment analysis data are gathered and pre-processed to ensure data quality. Feature engineering techniques are applied to extract relevant features, and forest-based machine learning algorithms are trained on the data to forecast stock prices. The Golden Ratio strategy is integrated into the trading model to identify the entry point and exit point. Empirical validation and performance evaluation demonstrate the effectiveness and robustness of the proposed approach. Through back testing and simulation-based testing, we evaluate the model's accuracy, profitability, and risk-adjusted returns. Our findings contribute to the advancement of algorithmic trading research and practice, offering insights into the potential benefits of combining machine learning algorithms with established trading strategies. The proposed hybrid model incorporates Golden Ratio Strategy, integrating Random Forest (RF). The results of the proposed random forest with Golden Ratio Strategy are compared with the results of individual model. This comparison helps in proving the efficiency of the proposed model. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

CDA-GNN: A Chain-driven Accelerator for Efficient Asynchronous Graph Neural Network 24

CDA-GNN: A Chain-driven Accelerator for Efficient Asynchrono...

引用

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Yu, Hui Zhang, Yu He, Ligang He, Donghao Li, Qikun Zhao, Jin Liao, Xiaofei Jin, Hai Gu, Lin Liu, Haikun National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Department of Computer Science University of Warwick United Kingdom

ISBN: (纸本)9798400706011

Asynchronous Graph Neural Network (AGNN) has attracted much research attention because it enables faster convergence speed than the synchronous GNN. However, existing software/hardware solutions suffer from redundant computation overhead and excessive off-chip communications for AGNN due to irregular state propagations along the dependency chains between vertices. This paper proposes a chain-driven asynchronous accelerator, CDA-GNN, for efficient AGNN inference. Specifically, CDA-GNN proposes a chain-driven asynchronous execution approach into novel accelerator design to regularize the vertex state propagations for fewer redundant computations and off-chip communications and also designs a chain-aware data caching method to improve data locality for AGNN. We have implemented and evaluated CDA-GNN on a Xilinx Alveo U280 FPGA card. Compared with the cutting-edge software solutions (i.e., Dorylus and AMP) and hardware solutions (i.e., BlockGNN and FlowGNN), CDA-GNN improves the performance of AGNN inference by an average of 1,173x, 182.4x, 10.2x, and 7.9x and saves energy by 2,241x, 242.2x, 12.4x, and 8.9x, respectively. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Graph neural networks

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：