检索结果-内蒙古大学图书馆

2024 IEEE High Performance Extreme Computing Conference, HPEC 2024

作者： Nauman, Hunter Di, Jia University of Arkansas Department of Electrical Engineering and Computer Science FayettevilleAR United States

ISBN: (纸本)9798350387131

The integrated circuit (IC) industry has experienced exponential growth in the complexity and scale of hardware designs. To sustain this growth, faster development cycles and cost-effective solutions have been the focus of many companies, notably through the incorporation of third-party intellectual property (IP). Outsourcing the production of sub-components reduces development time and enables faster time-to-market;however, this approach also introduces the threat of Hardware Trojans, which are malicious modifications or additions to an IC, posing significant security risks due to their small size, low activation frequency, and complex obfuscation techniques. This research proposes an advancement to the Trojan detection mechanisms incorporated in the Structural Checking Tool, a Trojan detection tool that focuses on the identification of logical Trojans embedded within soft IPs. Leveraging graph structures generated by the tool and signal-level features, this research develops a new dataset and three graph neural network architectures. Each neural network corresponds to classical graph neural network layers and execute graph-level probabilistic binary classification of Trojan inclusion. Through rigorous testing with two potential sets of node-level feature vectors, this research offers a faster, more accurate, and more adaptable approach than those existing within the current tool. © 2024 IEEE.

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

A Review of Power Electronics Converters in Hydrogen Fuel Cell Application 10

A Review of Power Electronics Converters in Hydrogen Fuel Ce...

引用

10th IEEE International Power Electronics and Motion Control Conference, IPEMC 2024 ECCE Asia

作者： Rahman, Mohammad Dehan Song, Xiaoqing University of Arkansas Department of Electrical Engineering and Computer Science FayettevilleAR United States

ISBN: (纸本)9798350351330

Hydrogen fuel cells offer a clean and efficient energy source for various applications, including transportation. However, the nonlinear output voltage and current characteristics of fuel cells present challenges in their utilization. Additionally, fuel cells typically exhibit a wide output voltage range, necessitating the use of a power converter to regulate the output voltage to the desired form. This paper aims to provide a comprehensive overview of power converters designed for fuel cell power generation and transportation applications. The survey will cover different converter topologies discussed in prior literature, summarizing the advantages and disadvantages of each. The insights gained from this survey aim to inform and guide future designs and developments in fuel cell-based power converters. © 2024 IEEE.

关键词： Fuel cells

来源：评论

学校读者我要写书评

暂无评论

A Phase Change Material Based Silicon Carbide Power Module Packaging 10

A Phase Change Material Based Silicon Carbide Power Module P...

引用

10th IEEE International Power Electronics and Motion Control Conference, IPEMC 2024 ECCE Asia

作者： Rahman, Mohammad Dehan Song, Xiaoqing University of Arkansas Department of Electrical Engineering and Computer Science FayettevilleAR United States

ISBN: (纸本)9798350351330

Most power electronics equipment like solar inverters or solid-state circuit breakers (SSCBs) require short-time overload current requirements, which subsequently necessitate the surge current capability of power semiconductor modules. Under overload current conditions, a significant amount of loss is generated inside the power modules within a short time period and heat up the semiconductor chip rapidly. To mitigate this, multiple power devices in parallel are usually needed which increases the circuit complexity and cost. An alternative way to address this is to increase the power module transient overload heat absorbing capability through advanced power module packaging techniques. In this paper, phase change materials (PCMs) are investigated and integrated in a silicon carbide (SiC) power module. With the PCM's latent heat capability, the SiC MOSFET power module is capable of providing an increased thermal capacity. The quantitative impact of using PCM on transient overload thermal performance is investigated. Finite element analysis model of SiC power module is built, and the junction temperature of the power module is simulated for both single-side and double-side cooling with PCM integrated. PCMs with different latent heat are also explored to study its effects on junction temperature. Experimental results using PCM validate the theoretical finite element model. Both the FEA and experimental analysis shows that use of PCM can significantly reduce temperature rise, thus helping in maintaining a more stable and controlled operating temperature. © 2024 IEEE.

关键词： Phase change materials

来源：评论

学校读者我要写书评

暂无评论

SHPIA 2.0: An Easily Scalable, Low-Cost, Multi-purpose Smart Home Platform for Intelligent Applications

引用

SN computer science 2024年第1期5卷 42页

作者： Demrozi, Florenc Turetta, Cristian Pravadelli, Graziano Department of Electrical Engineering and Computer Science University of Stavanger Stavanger Norway Department of Engineering for Innovation Medicine University of Verona Verona Italy

Sensors, electronic devices, and smart systems have invaded the market and our daily lives. As a result, their utility in smart home contexts to improve the quality of life, especially for the elderly and people with special needs, is getting stronger and stronger. Therefore, many systems based on smart applications and intelligent devices have been developed, for example, to monitor people’s environmental contexts, help in daily-life activities, and analyze their health status. However, most existing solutions have drawbacks related to accessibility and usability. They tend to be expensive and lack generality and interoperability. These solutions are not easily scalable and are typically designed for specific constrained scenarios. This paper tackles such drawbacks by presenting SHPIA 2.0, an easily scalable, low-cost, multi-purpose smart home platform for intelligent applications. It leverages low-cost Bluetooth Low Energy (BLE) devices featuring both BLE connected and BLE broadcast modes, to transform common objects of daily life into smart objects. Moreover, SHPIA 2.0 allows the collection and automatic labeling of different data types to provide indoor monitoring and assistance. Specifically, SHPIA 2.0 is designed to be adaptable to different home-based application scenarios, including human activity recognition, coaching systems, and occupancy detection and counting. The SHPIA platform is open source and freely available to the scientific community, fostering collaboration and innovation. © 2023, The Author(s).

关键词： Automatic data annotation Automatic data collection BLE broadcast mode BLE connected mode Human activity recognition Smart home platform

来源：评论

学校读者我要写书评

暂无评论

Power Density Limits of Propulsion Motor for Electric Aircraft: A Study on Insulation Thickness

Power Density Limits of Propulsion Motor for Electric Aircra...

引用

2024 International Conference on electrical Machines, ICEM 2024

作者： Wang, Jundong Dong, Jianning Niasar, Mohamad Ghaffarian Zhu, Gangwei Bauer, Pavol Delft University of Technology Department of Electrical Engineering Mathematics and Computer Science Delft Netherlands

ISBN: (纸本)9798350370607

This paper studies the power density limits of propulsion motor for electric aircraft considering thermal aspects and breakdown voltage reduction of insulation. The study em-ploys multi-objective optimization (MOO) to explore various mo-tor cooling options and filter configurations. The results show that motors with direct winding heat exchanger (DWHE) can reach higher specific power, while those equipped with water jacket cooling (WJC) offer a moderate design with simpler structure. Furthermore, the impact of sine wave and dv/dt filters on electric motors design is studied. The findings demonstrate that dv/dt filters enable designs with higher overall specific power compared to sine wave filters. Through simulations, this study identify the challenge faced by aviation motor design in significantly increased insulation thickness, necessitating advanced insulation materials with a minimum thermal conductivity of 5 W/(m.K) to facilitate a high specific power design. Based on this assumption, a preliminary design of 9.6 kW/kg with an efficiency of 98% is presented. © 2024 IEEE.

关键词： Thermal insulation

来源：评论

学校读者我要写书评

暂无评论

GrASPE: Graph Based Multimodal Fusion for Robot Navigation in Outdoor Environments

引用

IEEE Robotics and Automation Letters 2023年第12期8卷 8090-8097页

作者： Weerakoon, Kasun Sathyamoorthy, Adarsh Jagan Liang, Jing Guan, Tianrui Patel, Utsav Manocha, Dinesh University of Maryland Department of Electrical and Computer Engineering College ParkMD20740 United States University of Maryland Department of Computer Science College ParkMD20740 United States

We present a novel trajectory traversability estimation and planning algorithm for robot navigation in complex outdoor environments. We incorporate multimodal sensory inputs from an RGB camera, 3D LiDAR, and the robot's odometry sensor to train a prediction model to estimate candidate trajectories' success probabilities based on partially reliable multi-modal sensor observations. We encode high-dimensional multi-modal sensory inputs to low-dimensional feature vectors using encoder networks and represent them as a connected graph. The graph is then used to train an attention-based Graph Neural Network (GNN) to predict trajectory success probabilities. We further analyze the number of features in the image (corners) and point cloud data (edges and planes) separately to quantify their reliability to augment the weights of the feature graph representation used in our GNN. During runtime, our model utilizes multi-sensor inputs to predict the success probabilities of the trajectories generated by a local planner to avoid potential collisions and failures. Our algorithm demonstrates robust predictions when one or more sensor modalities are unreliable or unavailable in complex outdoor environments. We evaluate our algorithm's navigation performance using a Spot robot in real-world outdoor environments. We observe an increase of 10-30% in terms of navigation success rate and up to 15% increase in AU-ROC compared to the state-of-the-art navigation methods. © 2016 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

A Multi-Modal Framework for Fake News Analysis for Detection to Deconstruction 2

A Multi-Modal Framework for Fake News Analysis for Detection...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Vadakkethil Somanathan Pillai, Sanjaikanth E Parveen, H. Summia School of Electrical Engineering and Computer Science University of North Dakota Grand Forks United States Sri Eshwar College of Engineering Department of Computer Science Engineering Coimbatore India

ISBN: (纸本)9798350371055

The research discusses a multimodal framework for analyzing and detecting fake news and understanding its impact on society. This framework employs diverse strategies, including linguistic analysis, social network monitoring, and visual assessment, to capture various aspects of fabricated information and its dissemination. The first component of the framework focuses on linguistic analysis, examining the language and textual content used in fake news articles to identify misleading information, biased language, and sensationalized headlines. The second component analyzes the role of social networks in spreading fake news, tracking its propagation through platforms like social media and identifying key actors and influencers involved in its dissemination. The third component involves visual assessment, examining the images and videos used in fake news to manipulate public perceptions and emotions, including the detection of doctored images and misleading illustrations. © 2024 IEEE.

关键词： Fake News Detection Machine Learning NLP

来源：评论

学校读者我要写书评

暂无评论

Koopman-based Deep Learning for Nonlinear System Estimation 63

Koopman-based Deep Learning for Nonlinear System Estimation

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Sun, Zexin Chen, Mingyu Baillieul, John Boston University Division of Systems Engineering United States Boston University Department of Electrical and Computer Engineering United States Boston University Division of Systems Engineering Departments of Mechanical Engineering Electrical and Computer Engineering BostonMA02215 United States

ISBN: (纸本)9798350316339

Nonlinear differential equations are encountered as models of fluid flow, spiking neurons, and many other systems of interest in the real world. Common features of these systems are that their behaviors are difficult to describe exactly and invariably unmodeled dynamics present challenges in making precise predictions. In this paper, we present a novel data-driven linear estimator based on Koopman operator theory to extract meaningful finite-dimensional representations of complex non-linear systems. The Koopman model is used together with deep reinforcement networks that learn the optimal stepwise actions to predict future states of nonlinear systems. Our estimator is also adaptive to a diffeomorphic transformation of the estimated nonlinear system, which enables it to compute optimal state estimates without re-learning. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Accurate, Yet Scalable: A SPICE-based Design and Optimization Framework for eNVM-based Analog In-memory Computing 24

Accurate, Yet Scalable: A SPICE-based Design and Optimizatio...

引用

43rd International Conference on computer-Aided Design, ICCAD 2024

作者： Mojahidul Ahsan, S.M. Shahriar, Muhammad Sakib Chowdhury, Mrittika Hossain, Tanvir Hasan, Md Sakib Hoque, Tamzidul Department of Electrical Engineering and Computer Science University of Kansas LawrenceKS United States Department of Electrical and Computer Engineering University of Mississippi OxfordMS United States

ISBN: (纸本)9798400710773

This paper introduces a scalable SPICE-based tool infrastructure designed to optimize analog compute-in-memory (ACIM) architectures utilizing emerging non-volatile resistive memory (eNVM) technologies. The inherent efficiency of analog eNVM crossbar arrays in performing matrix-vector multiplications significantly enhances the power, performance, and area efficiency of edge AI devices and other applications. Our framework addresses the challenges of accurately simulating ACIM architectures, which are highly susceptible to variations in process, voltage, temperature, and analog noise. The framework uses SPICE for accurate analog and mixed-signal circuit simulation. It automates the generation of SPICE-level ACIM designs for deep neural networks. Additionally, it speeds up the simulation runtime by up to 35× for large DNN models while maintaining the same SPICE-level accuracy. Moreover, it ensures simulation convergence for large netlists, facilitating SPICE simulation of large-scale eNVM crossbars that were previously impractical. We demonstrated that our framework is capable of simulating inference using netlists for MLPs with over 800,000 parameters trained on the MNIST dataset within acceptable runtime, where contemporary SPICE simulators do not even converge. We validated the simulation results in terms of inference accuracy, which shows less than a 3.8% accuracy drop compared to software-based inference results. Lastly, we demonstrated the integration of our framework with an architectural simulator, facilitating comprehensive system-level simulation. © 2024 Copyright is held by the owner/author(s).

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Federated Learning under Sample Selection Heterogeneity

Federated Learning under Sample Selection Heterogeneity

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Mai, Huy Wu, Xintao University of Arkansas Department of Electrical Engineering and Computer Science FayettevilleAR United States

ISBN: (纸本)9798350362480

Despite having benefits of privacy preservation and secure computation, federated learning (FL) faces the issue of data heterogeneity. Specifically, the performance of FL systems can be degraded due to sample selection heterogeneity. We define the sample selection heterogeneity scenario with two points. First, each local training set is subject to missing-not-at-random (MNAR) sample selection bias where some labels are non-randomly missing. This requires incorporating a sample selection model that utilizes two equations to account for the prediction and selection of samples. Choosing selection features is a challenging task, especially when the number of observed features is large. Second, the sample selection mechanism is not the same across all clients. This implies that clients do not share the same set of selection features. In this work, we propose FL-MNAR to address FL under sample selection heterogeneity. The framework integrates an existing sample selection model that robustly handles sample selection bias for each client. FL-MNAR also trains an assignment function that gives a set of selection features to each client based on how well the features fit selection. Experimental results show that FL-MNAR achieves state-of-the-art performance under sample selection heterogeneity. © 2024 IEEE.

关键词： Federated learning

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：