检索结果-内蒙古大学图书馆

IEEE computer Society Conference on computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Xingjian Li Jeremy Park Chris Reberg-Horton Steven Mirsky Edgar Lobaton Lirong Xiang Department of Biological and Agricultural Engineering North Carolina State University Department of Electrical and Computer Engineering North Carolina State University Department of Computer Science North Carolina State University Department of Crop and Soil Science North Carolina State University Sustainable Agricultural Systems Laboratory USDA-ARS

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Robotics paired with computer vision are widely used in precision agriculture. Simulations are critical for safety and performance estimation by verifying their routine in a virtual world before real-world testing and deployment. However, many simulators used in agricultural robots lack photorealism in their virtual worlds compared to the real world. We implemented Unreal Engine 5 (UE5) and the Robot Operating System (ROS) to develop a robot simulator tailored to agricultural tasks and synthetic data generation with RGB, segmentation, and depth images. We designed a method for assigning multiple segmentation labels within a single plant mesh. We experimented with a semi-spherical routine for two robot arms to perform 3D point cloud reconstruction across 10 plant assets. We showed our simulator produces much more accurate segmentation images and reconstruction compared to existing UE5 solutions. We extend our results with Neural Radiance Field (NeRF) reconstructions. The packaged simulator, UE5 project, and ROS package with the Python routine can be found at https://***/NCSU-BAE-ARLab/AgriRoboSimUE5.

关键词： Image segmentation computer vision Three-dimensional displays Computational modeling Neural radiance field Manipulators Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Invertible Voice Conversion with parallel Data

Invertible Voice Conversion with Parallel Data

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zexin Cai Ming Li Department of Electrical and Computer Engineering Duke University Durham NC USA Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems Duke Kunshan University Kunshan PR China

This paper introduces an innovative deep learning framework for parallel voice conversion to mitigate inherent risks associated with such systems. Our approach focuses on developing an invertible model capable of countering potential spoofing threats. Specifically, we present a conversion model that allows for the retrieval of source voices, thereby facilitating the identification of the source speaker. This framework is constructed using a series of invertible modules composed of affine coupling layers to ensure the reversibility of the conversion process. We conduct comprehensive training and evaluation of the proposed framework using parallel training data. Our experimental results reveal that this approach achieves comparable performance to non-invertible systems in voice conversion tasks. Notably, the converted outputs can be seamlessly reverted to the original source inputs using the same parameters employed during the forwarding process. This advancement holds considerable promise for elevating the security and reliability of voice conversion.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Wavelet Convolutional Neural Network for Low-Resolution Brain MRI Images

Wavelet Convolutional Neural Network for Low-Resolution Brai...

引用

IEEE International Symposium on Biomedical Imaging

作者： Soo Min Oh Yifan Li Jo Woon Chong Wireless Information and Network Sciences Laboratory Massachusetts Institute of Technology Cambridge MA USA Laboratory for Information and Decision Systems Massachusetts Institute of Technology Cambridge MA USA Department of Statistics Texas A&M University College Station TX USA Department of Electrical and Computer Engineering Texas Tech University Lubbock TX USA Department of Electrical and Computer Engineering Sungkyunkwan University Suwon Korea

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Low-resolution images inherently contain less information, making effective feature extraction more challenging and posing difficulties for training neural networks. However, if neural networks can be trained successfully on low-resolution images, this could significantly reduce memory storage requirements and computational costs. In this study, we address the limitations of low-resolution brain MRI images by enhancing the available information through wavelet transform techniques. Specifically, we leverage the high-frequency coefficients obtained from wavelet transforms and the Hurst exponent to improve feature representation and optimize model training for convolutional neural networks (CNN), which is referred to as the wavelet CNN (WCNN). We demonstrate that WCNN outperforms standard CNNs in multi-class classification tasks, distinguishing among four categories of brain MRI images such as normal, glioma, meningioma, and pituitary tumor images. This approach highlights the potential to achieve high classification accuracy even with low-resolution data, ultimately reducing the memory and computational resources required for data processing and model training.

关键词： Wavelet transforms Training Accuracy Magnetic resonance imaging Computational modeling Brain modeling Feature extraction Data models Convolutional neural networks Tumors

来源：评论

学校读者我要写书评

暂无评论

Exploration of the Role of Cryptoprocessors in Advancing IoT Security

Exploration of the Role of Cryptoprocessors in Advancing IoT...

引用

International Conference on Distributed Computing in Sensor systems (DCOSS)

作者： Elena Kakoulli Eleftherios Zacharioudakis Department of Computer Science Intelligent Systems Laboratory Neapolis University Pafos Pafos Cyprus Electrical Engineering and Computer Engineering and Informatics Cyprus University of Technology Limassol Cyprus Igor Sikorsky Kyiv Polytechnic Institute National Technical University of Ukraine Kyiv Ukraine

ISBN: (数字)9798350369441

ISBN: (纸本)9798350369458

This paper presents a thorough exploration of Cryptoprocessors in the context of the Internet of Things (IoT). The focus is on hardware support, cryptographic processors, and energy-efficient designs to fortify the security of IoT ecosystems. Leveraging insights from recent research papers, the survey examines various aspects of Cryptoprocessor implementations, ranging from lightweight countermeasures to advanced lattice-based post-quantum cryptography. The proposed paper amalgamates findings from studies on hardware architectures, energy-efficient designs, and innovative cryptographic algorithms to provide a holistic overview of state-of-the-art advancements in IoT security. The synthesis of this survey’s exploration aims to contribute to the ongoing discourse on securing IoT devices through robust hardware-backed cryptographic solutions.

关键词： Surveys Industries Technological innovation Program processors Ecosystems Hardware Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Fault Tolerant Control Allocation Scheme for LPV system

Fault Tolerant Control Allocation Scheme for LPV system

引用

Control Conference (ANZCC), Australian and New Zealand

作者： Salman Ijaz Ahmed Nasr Mirza Tariq Hamayun Key Laboratory of More Electric Aircraft Zhejiang Province and members of Control Systems laboratory University of Nottingham Ningbo China Department of Electrical and Computer Engineering COMSATS University Islamabad Lahore Campus Pakistan

This paper proposed a passive fault tolerant control (FTC) approach for the class of linear parameter-varying systems to deal with faults and failures in the actuator channel. The method provided in this study combines the robustness feature of integral sliding mode control (ISMC) and control allocation (CA) obtained through singular value decomposition of the input matrix. The purpose is to effectively handle faults and failures along the entire operating spectrum, which involves various scheduling parameters. This technique is effective because the same baseline controller, initially developed for a nominal system, can deal with a wide range of faults and failures without acquiring fault information. The performance of ISM-FTC is tested on a longitudinal model of aircraft system. Numerical simulations indicate no noticeable difference in tracking performance between nominal and faulty conditions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

VersaSens: An Extendable Multimodal Platform for Next-Generation Edge-AI Wearables

IEEE Transactions on Circuits and Systems for Artificial Int...

引用

IEEE Transactions on Circuits and systems for Artificial Intelligence 2024年第1期1卷 83-96页

作者： Taraneh Aminosharieh Najafi José Angel Miranda Calero Jérôme Thevenot Benjamin Duc Stefano Albini Alireza Amirshahi Hossein Taji María José Belda Beneyto Antonio Affanni David Atienza Embedded Systems Laboratory (ESL) Institute of Electrical and Micro Engineering École Polytechnique Fédérale de Lausanne (EPFL) Lausanne Switzerland Polytechnic Department of Engineering and Architecture Udine Italy Computer Architecture and Automation Department Universidad Complutense de Madrid Madrid Spain

The transition of healthcare towards digitalization is closely related to the advancement of health-related technologies, including wearable sensors and edge computing. In this paper, we present VersaSens, a versatile and customizable platform concept and its real implementation as a tool to boost research in wearable sensors. The platform embodies the core attributes of the VersaSens concept: versatility, flexibility, and extendability across multiple aspects of hardware, software, and processing components. It features a modular design, consisting of sensor, processor, and co-processor modules, allowing for various configurations. To evaluate the efficiency of the platform, we tested three use cases: cough monitoring, heartbeat classification and epileptic seizure detection. In all cases, the results indicate that the platform effectively executes the applications, achieving low energy consumption. In particular, our findings indicates that the integration of a domain-specific edge-AI co-processor [i.e., HEEP ocrates (Machetti et al., 2024)] equipped with several hardware accelerators further improved the overall execution time and energy consumption of the system. These results demonstrate the potential of VersaSens to effectively support a diverse range of edge-AI applications and configurations, thereby providing a robust foundation for the research and development of novel smart wearable sensor systems.

关键词： Sensors Wearable devices Artificial intelligence Wearable sensors Medical services Intelligent sensors Monitoring

来源：评论

学校读者我要写书评

暂无评论

An Optimal Bipolar MVDC Coaxial Power Cable Design for Envisaged All Electric Wide Body Aircraft

An Optimal Bipolar MVDC Coaxial Power Cable Design for Envis...

引用

Conference on electrical Insulation and Dielectric Phenomena, (CEIDP)

作者： Anoy Saha Arian Azizi Mona Ghassemi Department of Electrical and Computer Engineering Zero Emission Realization of Optimized Energy Systems (ZEROES) Laboratory The University of Texas at Dallas Richardson TX USA

Future generations of electrified aircraft, such as more electric aircraft (MEA) and all-electric aircraft (AEA), will require high-power-delivery and low-system-mass electric power systems (EPS). Designing aircraft cables confronts thermal challenges due to the limited heat transfer by convection at a cruising altitude of 12.2 km (18.8 kPa) for wide-body aircraft. These thermal challenges are exacerbated by implementing bipolar MVDC EPSs which are formed of two adjacent power cables, conventionally. In this regard, coaxial geometry for cables can be evaluated as a solution to this problem. In this paper, a coaxial MVDC power cable is, for the first time, designed with inner and outer conductors carrying the same ampacity of 1000 A when the voltage of the inner and outer conductors is −5 kV and +5 kV, respectively. This design compares the effectiveness of coaxial power cables to the conventional arrangement of bipolar MVDC cable systems. This study will analyze three case studies to determine if a coaxial geometry is better than a conventional arrangement for a bipolar MVDC cable system or not. According to the findings of this study, coaxial cable requires thicker insulation and more conductors to maintain the same maximum electric field norm within cable insulation and ampacity. As a result, coaxial cables result in a greater mass and cross-sectional area than standard bipolar cables. For the envisaged AEA, the investigation in this paper addresses questions about the performance of coaxial geometry for bipolar MVDC power cables.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hybrid Sub-Harmonic Synchronous Machines Using Series and parallel Consequent Permanent Magnet

Hybrid Sub-Harmonic Synchronous Machines Using Series and Pa...

引用

IEEE Energy Conversion Congress and Exposition, ECCE

作者： S M Sajjad Hossain Rafin Qasim Ali Osama A. Mohammed Dept. of Electrical and Computer Engineering Energy Systems Research Laboratory Florida International University Miami Florida USA Department of Electrical Engineering Sukkur IBA University Sukkur Pakistan

This paper presents novel sub-harmonic synchronous machines having series or parallel permanent magnet structures on rotors for better performance in terms of greater torque density. The stator of the machines has two sets of three-phase winding, where the additional winding is used to generate sub-harmonic magnetomotive force components for brushless operation. Similar to the stator, the rotor of them uses an additional winding to induce that sub-harmonic component. Rotor also uses a permanent magnet to improve machine performance in series or parallel hybrid structures having conventional or consequent pole permanent magnet structures. In this paper, 4 different rotors, 3 having hybrid excitation, are used and their performance is compared. To validate the performance, a 2D finite element analysis of 8 poles and 48 slots of sub-harmonic synchronous machines is carried out with different rotors. Finally, the wide-speed operation of the proposed machine is discussed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Test System for Transmission Expansion Planning Studies Meeting the Operation Requirements Under Normal Condition as Well as all Single Contingencies

A Test System for Transmission Expansion Planning Studies Me...

引用

Annual North-American Power Symposium

作者： Bhuban Dhamala Mona Ghassemi Department of Electrical and Computer Engineering Zero Emission Realization of Optimized Energy Systems (ZEROES) Laboratory The University of Texas at Dallas Richardson TX USA

This paper presents a 17-bus 500 kV test system for transmission expansion planning (TEP) studies. An actual 500 kV transmission line geometry was used for the overhead lines of this system. Although many test systems have been introduced for different types of power system analysis, those especially for TEP studies at a transmission voltage level, not distribution voltage level, are few. To the best of our knowledge, the introduced test systems for TEP studies, either those combined with electricity market problems or those used to connect a new load or generation to an existing power grid, consider the studies under only normal condition. However, for TEP studies it is needed that a test system meets voltage drop and line loading limits criteria under normal condition as well as all single contingencies, and in this regard, addressing the latter, all single contingencies, is challenging. This paper addresses this technical gap, introducing a 17-bus test system at a transmission voltage level, 500 kV, that meets requirements under normal condition as well as all single contingencies. In addition to presenting all details of this new test system, load flow results under normal condition as well as the worst single contigency are presented. For studies on the TEP, this test system can be an invaluable resource.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Cuboid Geometry Design for MVDC Power Cables for Using in Future All Electric Wide Body Aircraft

A Cuboid Geometry Design for MVDC Power Cables for Using in ...

引用

Conference on electrical Insulation and Dielectric Phenomena, (CEIDP)

作者： Arian Azizi Anoy Saha Mona Ghassemi Department of Electrical and Computer Engineering Zero Emission Realization of Optimized Energy Systems (ZEROES) Laboratory The University of Texas at Dallas Richardson TX USA

Designing high-power-delivery and low-system-mass electric power systems (EPS) is a major goal to achieve the next generation of electrified aircraft. As one of its major components, cables must be redesigned to obtain high-power-density and low-system-mass EPS. Among challenges in designing aircraft cables such as arc and arc tracking, partial discharges (PD), and thermal management, the latter is decisive since the thermal properties of the cable determine its maximum ampacity. The maximum permissible current of a cable depends on radiative and convective heat transfers from its surface to the ambient environment. At the cruising altitude (12.2 km) of wide-body aircraft where the air pressure is 18.8 kPa, the convective heat transfer is greatly reduced which results in a reduction in maximum permissible current. Moreover, both radiative and convective heat transfers depend on the surface area of the cable. One way to increase the heat transfers and compensate for the reduction of convective heat transfer from a limited air pressure is to change the geometry of the cable. The cuboid geometry design provides a larger contact area with the ambient environment for the same cross-section area, so it is expected that the heat transfer will increase compared to conventional cylindrical cables, and in turn, the maximum power carrying capacity of the cable will be larger. Here, the question is whether the hypothesis is true, and if so, how much improvement can be expected. The purpose of this paper is to answer these questions and, for the first time, an MVDC (5 kVdc) high power (1 kA) cuboid shape cable is designed for future AEA to increase the maximum permissible current of the cable.

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：