检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Ghosh, Shreya Chen, Yi-Huan Huang, Ching-Hsiang Jameel, Abu Shafin Mohammad Mahdee Ho, Chien Chou Gamal, Aly El Labi, Samuel School of Electrical and Computer Engineering Purdue University United States

A significant challenge in racing-related research is the lack of publicly available datasets containing raw images with corresponding annotations for the downstream task. In this paper, we introduce RoRaTrack, a novel dataset that contains annotated multi-camera image data from racing scenarios for track detection. The data is collected on a Dallara AV-21 at a racing circuit in Indiana, in collaboration with the Indy Autonomous Challenge (IAC). RoRaTrack addresses common problems such as blurriness due to high speed, color inversion from the camera, and absence of lane markings on the track. Consequently, we propose RaceGAN, a baseline model based on a Generative Adversarial network (GAN) that effectively addresses these challenges. The proposed model demonstrates superior performance compared to current state-of-the-art machine learning models in track detection. The dataset and code for this work are available at ***/RaceGAN. Copyright © 2025, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Active Data Acquisition–An Information Theoretic Approach

Active Data Acquisition–An Information Theoretic Approach

引用

International Conference on Computing, networking and Communications (ICNC)

作者： An Vuong Anthony Q Nguyen Thinh Nguyen School of Electrical and Computer Engineering Oregon State University Corvallis OR

ISBN: (数字)9798331520960

ISBN: (纸本)9798331520977

Insufficient data acquisition can lead to information loss, which may result in inaccurate classifications when using the database for supervised learning. On the other hand, expanding data collection comes with its own set of challenges, such as higher costs for data acquisition, storage, and extraction, as well as the risk of gathering and processing irrelevant data for specific purposes. To that end, we propose an information-theoretic framework to address the problem of data acquisition and classification under resource constraints. An information-theoretic perspective offers a valuable approach to balancing specificity and generality in the active data acquisition problem. Instead of merely optimizing data acquisition to improve the accuracy of a particular learning algorithm, our goal is to collect data with the most relevant information for a broad range of potential tasks, under the resource constraints, and without involving specific learning algorithm in the process. Specifically, we use mutual information to quantify the relevance of the data for these tasks since it is more robust than other measures, and is not tied to any particular types of learning algorithms.

关键词： Measurement Hands Accuracy Simulation Data acquisition Supervised learning Data collection Entropy Classification algorithms Mutual information

来源：评论

学校读者我要写书评

暂无评论

Greeting Gesture Analysis Using Boosting Algorithms and SHAP 13

Greeting Gesture Analysis Using Boosting Algorithms and SHAP

引用

Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2024

作者： Wibowo, Angga Wahyu Sato-Shimokawara, Eri Kurnianingsih Graduate School of Systems Design Tokyo Metropolitan University Department of Computer Science Tokyo Japan Politeknik Negeri Semarang Department of Electrical Engineering Semarang Indonesia

ISBN: (纸本)9798350373332

Recently, studies related to human activity recognition have developed which have been applied in various fields. In that field Machine learning and deep learning techniques have been widely used for several classification and prediction tasks. However, the first problem is that there is rarely any research on human activities that reflect the culture of a region, such as greeting gestures. Second, there are few studies that do not provide models resulting from the classification or prediction process using machine learning, which can result in a lack of understanding of how a model from machine learning is generated. This study aims to predict Japanese greeting gestures (eshaku, keirei, saikeirei, waving hand) and Indonesian (placing both hands in front of the chest) using Light Gradient Boosting Machine (LightGBM), eXtreme Gradient Boosting (XGBoost), and Gradient Boosting. Then, represent the model of the learning machine using SHapley Additive exPlanations (SHAP) to find out how the learning machine obtain a model. Our findings show the efficacy of this method and show that the model not only predicts greeting gestures with high accuracy but also offers a transparent understanding of the factors influencing its predictions, thus enhancing the interpretability and applicability of machine learning in recognizing culturally significant human activities. In the future, we plan to use machine learning and other Explainable Artificial Intelligence (XAI) methods to study human activities with cultural concepts such as greeting gestures in different styles, create more greeting gesture-based human activity datasets, and examine the ethical implications or considerations of using machine learning in cultural contexts to respect cultural differences. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Online Experimental Design for Causal Discovery 41

Adaptive Online Experimental Design for Causal Discovery

引用

41st International Conference on Machine Learning, ICML 2024

作者： Elahi, Muhammad Qasim Wei, Lai Kocaoglu, Murat Ghasemi, Mahsa School of Electrical and Computer Engineering Purdue University West LafayetteIN United States Life Sciences Institute University of Michigan Ann ArborMI United States

Causal discovery aims to uncover cause-and-effect relationships encoded in causal graphs by leveraging observational, interventional data, or their combination. The majority of existing causal discovery methods are developed assuming infinite interventional data. We focus on interventional data efficiency and formalize causal discovery from the perspective of online learning, inspired by pure exploration in bandit problems. A graph separating system, consisting of interventions that cut every edge of the graph at least once, is sufficient for learning causal graphs when infinite interventional data is available, even in the worst case. We propose a track-and-stop causal discovery algorithm that adaptively selects interventions from the graph separating system via allocation matching and learns the causal graph based on sampling history. Given any desired confidence value, the algorithm determines a termination condition and runs until it is met. We analyze the algorithm to establish a problem-dependent upper bound on the expected number of required interventional samples. Our proposed algorithm outperforms existing methods in simulations across various randomly generated causal graphs. It achieves higher accuracy, measured by the structural hamming distance (SHD) between the learned causal graph and the ground truth, with significantly fewer samples. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Delay-Aware Approach for Distributed Embedding Towards Cross-Slice Communication 2

A Delay-Aware Approach for Distributed Embedding Towards Cro...

引用

2nd IEEE International Mediterranean Conference on Communications and networking, MeditCom 2022

作者： Dimolitsas, Ioannis Spatharakis, Dimitrios Dechouniotis, Dimitrios Papavassiliou, Symeon School of Electrical and Computer Engineering National Technical University of Athens Athens Greece

ISBN: (数字)9781665498258

ISBN: (纸本)9781665498258

The evolution of modern applications and the adoption of the 5G network slicing architecture require minimizing the communication delays. Virtual network Functions (VNFs) offer low latency services to remote users. In the context of Edge Computing, these virtualized services are hosted in Edge Clouds, which, however, have limited resources. Embedding the network Slice requests from users is a challenging problem, and demands distributed solutions in the presence of resource and delay constraints in the Edge network. This paper introduces a distributed delay-aware service discovery mechanism, which performs cache-based forwarding, trying to efficiently discover VNFs in the Edge Clouds (ECs) and enable Cross-Slice Communication (CSC);that is the sharing of common VNFs between different network Slices (NSes). Furthermore, the distributed NS embedding (NSE) problem is addressed by a modified k-Shortest Path (k-SP) approach to minimize the total round-trip network delay under the capacity constraints of the underlying infrastructures. The proposed method significantly decreases the execution time by 70% to provide the distributed NSE solution compared to the baseline k-SP algorithm. © 2022 IEEE.

关键词： network function virtualization

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Technique for Mutual Coupling Reduction in a Compact Dual-Band Millimeter-Wave MIMO Antenna

引用

IEEE Antennas and Wireless Propagation Letters 2025年

作者： Ahmad, Jawad Hashmi, Mohammad Falcone, Francisco Nazarbayev University Department of Electrical and Computer Engineering School of Engineering and Digital Sciences Astana Kazakhstan Pamplona Spain

This letter reports a hybrid approach employing metallic vias and metasurface for mutual coupling reduction in a MIMO antenna at mmWave frequencies. Initially, a dual-band coaxial-fed antenna, operating at 27 GHz and 28 GHz, is designed using modified K-shaped patch arms with a tapered profile which is then used to develop a four-element dual-band MIMO array. Subsequently, metallic vias are incorporated to suppress surface wave-induced coupling. Finally, metasurface slab is integrated to mitigate near-field interactions. The proposed design achieves an impedance bandwidth of 26.75-27.28 GHz and 27.77-28.19 GHz, with coupling levels below 30 dB, and broadside radiation patterns with respective peak gains of 6.52 dBi and 6.74 dBi. Furthermore, the proposed design exhibits an envelope correlation coefficient (ECC) of less than 0.05 for isotropic and less than 0.25 for Gaussian environments. An excellent agreement between the experimental and simulation results validate the proposed design approach. © 2025 IEEE.

关键词： Microwave antennas

来源：评论

学校读者我要写书评

暂无评论

Investigating Handover Behavior with 5G and beyond TurboRAN Testbed 7

Investigating Handover Behavior with 5G and beyond TurboRAN ...

引用

7th International Conference on Mobile and Secure Services, MobiSecServ 2022

作者： Nabeel, Muhammad Manalastas, Marvin Ijaz, Aneeqa Refai, Hazem Imran, Ali University of Oklahoma School of Electrical Computer Engineering TulsaOK United States

ISBN: (纸本)9781728188379

With a recent roll out of Fifth Generation (5G), the focus of cellular industry and research community is now turned towards Sixth Generation (6G). The aim of 6G is to provide substantially higher capacity, seamless connectivity, better energy efficiency, spectral efficiency, reliability, and latency among others. To achieve this goal, new technologies and concepts are being proposed, however, to demonstrate their actual performance, it is important to integrate them in practical networks and then analyze the performance. Nowadays, testbeds are considered as an essential tool to evaluate realistic performance of cellular networks. Nevertheless, deploying a large-scale testbed often involves complex steps including network, site planning and choosing the appropriate hardware. In this work, we present our newly deployed TurboRAN testbed, and report all the findings, that are indispensable for evaluating different concepts of next generation cellular networks. The TurboRAN testbed is a complete integrated mobile cellular network deployed over 300 000 m2 area with the combination of indoor and outdoor cell deployment. It supports a variety of essential cellular networks features and aims to offer free access to the community for conducting experiments. In order to illustrate some of the capabilities of TurboRAN, in this work, we also investigate handover procedure and mobility management in different settings. In a nutshell, this work serves as a guide for readers who are planning to deploy a testbed for 5G and Beyond testing networks. © 2022 IEEE.

关键词： Testbeds

来源：评论

学校读者我要写书评

暂无评论

Techno-Economical Assessment of AC and DC Power Distribution Architectures for Data Centers

Techno-Economical Assessment of AC and DC Power Distribution...

引用

2022 North American Power Symposium, NAPS 2022

作者： Chen, Yiming Grijalva, Santiago Graber, Lukas Seyedi, Younes Georgia Institute of Technology School of Electrical and Computer Engineering Atlanta United States

ISBN: (纸本)9781665499217

The data center industry has been experiencing unprecedented growth in recent years due to the increasing demand for cloud-based computing services. Modern data centers require efficient power distribution architectures to improve their reliability while reducing their costs. The recent development of efficient and ultra-fast medium voltage DC breakers enables new DC and hybrid AC/DC architectures. This paper proposes a techno-economic framework for assessing AC/DC power distribution architectures in data centers, which uses a comprehensive set of economic value streams. Different architectures are evaluated and compared, namely low-voltage AC (LVAC), low-voltage DC (LVDC), medium-voltage AC (MVAC), and medium-voltage DC (MVDC) systems. Numerical results show that the LVDC and MVDC architectures can significantly reduce the capital cost of data centers while maintaining a high level of system efficiency. However, the MVDC architecture outperforms the other cases as wide bandgap (WBG) devices prevail as options for power converters. © 2022 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Safety-Guided Test Generation for Structural Faults

Safety-Guided Test Generation for Structural Faults

引用

2024 IEEE International Test Conference, ITC 2024

作者： Tan, Xuanyi Thapar, Dhruv Sahoo, Deepesh Chaudhuri, Arjun Banerjee, Sanmitra Chakrabarty, Krishnendu Parekhji, Rubin School of Electrical Computer and Energy Engineering AZ United States Asu Center for Semiconductor Microelectronics United States Pvt. Ltd. Bangalore India

ISBN: (纸本)9798331520137

Many real-life safety-critical applications such as autonomous driving require functional safety. We present a framework for functional safety-guided test pattern generation. We incorporate the functional information of each standard cell into a multi-layer-perceptron (MLP), referred to as Cell-Net. Each Cell-Net is a pre-trained MLP that models the behavior of the corresponding standard cell. The design netlist is translated into its neural twin, where the standard cell instances are substituted by their corresponding Cell-Nets and the wires in the netlist translate to neural connections between these Cell-Nets. We leverage the neural twin-enabled back-propagation for gradient computation, and utilize these gradients to compute test patterns. The output of every Cell-Net is associated with a bias that represents a perturbation in the signal propagating through that Cell-Net. We manipulate these bias values to inject stuck-at faults at the output of Cell-Nets. We utilize the neural twin to enhance the propagation of faults to primary outputs (POs), and find the test patterns that maximize the propagation of faults to POs. The neural twin also enables the assignment of non-binary criticalityfactors (CFs) to different POs and perform a test-pattern search for each fault for a given CF configuration. Our results on five benchmark circuits across three different CF configurations show an increased fault propagation achieved by the neural twin as compared to Automatic Test Pattern Generation (ATPG). © 2024 IEEE.

关键词： Automatic test pattern generation

来源：评论

学校读者我要写书评

暂无评论

Reviewing metal supported solid oxide fuel cells for efficient electricity generation with biofuels for mobility

引用

Journal of Energy Chemistry 2025年第4期103卷 106-153页

作者： Fábio C.Antunes João P.J.de Oliveira Ricardo S.de Abreu Thiago Dias Bruno B.N.S.Brandão Josué M.Gonçalves Josimar Ribeiro Julian Hunt Hudson Zanin Gustavo Doubek School of Electrical and Computer Engineering University of CampinasCampinas 13083-852Brazil School of Food Engineering University of CampinasCampinas 13083-852Brazil School of Chemical Engineering University of CampinasCampinas 13083-852Brazil Mackenzie Institute for Research in Graphene and Nanotechnologies(MackGraphe) Mackenzie Presbyterian InstituteSão Paulo 01302-907Brazil Electrochemistry Research and Development Laboratory(LPDE) Department of ChemistryCenter of Exact SciencesFederal University of Espírito SantoCampus GoiabeirasVitória 29075-910Brazil Biological and Environmental Science and Engineering Division King Abdullah University of Science and TechnologyThuwal 23955-6900Saudi Arabia

Metal-Supported Solid Oxide Fuel Cells(MS-SOFCs)hold significant potential for driving the energy *** electrochemical devices represent the most advanced generation of Solid Oxide Fuel Cell(SOFCs)and can pave the way for mass production and wider adoption than Proton Exchange Membrane Fuel Cells(PEMFCs)due to their fuel flexibility,higher power density and the absence of noble metals in the fabrication *** review examines the state-of-the-art of SOFCs and MS-SOFCs,presenting perspectives and research directions for these key technological devices,highlighting novel materials,techniques,architectures,devices,and degradation mechanisms to address current challenges and future *** such as infiltration/impregnation,ex-solution catalyst synthesis,and the use of a pre-catalytic reformer layer are discussed as their impact on efficiency and prolonged *** concepts are also described and connected with well-dispersed nano particles,hindrance of coarsening,and an increased number of Triple Phase Boundaries(TPBs).This review also describes the synergistic use of reformers with MS-SOFCs to compose solutions in energy generation from readily available ***,the End-of-Life(EoL),recycling,and life-cycle assessments(LCAs)of the Fuel Cell Hybrid Electric Vehicles(FCHEVs)were *** comparing Fuel Cell Electric Vehicles(FCEVs)equipped with(PEMFCs)and FCHEVs equipped with MS-SOFCs,both powered with hydrogen(H_(2))generated by different routes were *** review aims to provide valuable insights into these key technological devices,emphasizing the importance of robust research and development to enhance performance and lifespan while reducing costs and environmental impact.

关键词： Reform Metal-supported solid oxide fuel cell Powertrain systems Fuel cell Hybrid electric vehicle Biofuel

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：