检索结果-内蒙古大学图书馆

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Fangzhou Lin Haotian Liu Haoying Zhou Songlin Hou Kazunori D Yamada Gregory S. Fischer Yanhua Li Haichong K. Zhang Ziming Zhang Department of Robotics Engineering Worcester Polytechnic Institute Worcester MA USA Graduate School of Information Sciences Tohoku University Sendai Japan Dell Technologies Hopkinton MA USA Department of Computer Science Worcester Polytechnic Institute Worcester MA USA Department of Electrical & Computer Engineering Worcester Polytechnic Institute Worcester MA USA

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

3D point clouds enhanced the robot’s ability to perceive the geometrical information of the environments, making it possible for many downstream tasks such as grasp pose detection and scene understanding. The performance of these tasks, though, heavily relies on the quality of data input, as incomplete can lead to poor results and failure cases. Recent training loss functions designed for deep learning-based point cloud completion, such as Chamfer distance (CD) and its variants (e.g. HyperCD [1]), imply a good gradient weighting scheme can significantly boost performance. However, these CD-based loss functions usually require data-related parameter tuning, which can be time-consuming for data-extensive tasks. To address this issue, we aim to find a family of weighted training losses (weighted CD) that requires no parameter tuning. To this end, we propose a search scheme, Loss Distillation via Gradient Matching, to find good candidate loss functions by mimicking the learning behavior in backpropagation between HyperCD and weighted CD. Once this is done, we propose a novel bilevel optimization formula to train the backbone network based on the weighted CD loss. We observe that: (1) with proper weighted functions, the weighted CD can always achieve similar performance to HyperCD, and (2) the Landau weighted CD, namely Landau CD, can outperform HyperCD for point cloud completion and lead to new state-of-the-art results on several benchmark datasets. Our demo code is available at https://***/Zhang-VISLab/IROS2024-LossDistillationWeightedCD.

关键词： Point cloud compression Training Three-dimensional displays Laser radar Benchmark testing Iterative algorithms Tuning Optimization Intelligent robots Convergence

来源：评论

学校读者我要写书评

暂无评论

RANFusion: A Comprehensive Tool for Simulating Handover In Next-G RAN

RANFusion: A Comprehensive Tool for Simulating Handover In N...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Seyed Bagher Hashemi Natanzi Bo Tang Electrical and Computer Engineering Worcester Polytechnic Institute Massachusetts USA

ISBN: (数字)9798331517786

ISBN: (纸本)9798331517793

The rapid advancement of 5G networks and the upcoming transition to 6G necessitate the use of the Open Radio Access Network (O-RAN) architecture to enable greater flexibility, interoperability, and innovation. This shift towards 6G and O-RAN requires the development of advanced simulation tools for testing, analyzing, and optimizing Radio Access Network (RAN) operations. This need becomes critical due to the complex dynamics of mobility management inherent in the 6G vision and next-generation networks. These networks anticipate advanced handover methods for mobile users, UAVs, IoT devices, and beyond. Addressing this gap, this paper introduces RANFusion: a robust RAN simulator specifically created to explore a variety of handover scenarios and to test and balance resources between users. This tool enables precise simulations for refining handover strategies within RAN and O-RAN environments, thereby ensuring optimal performance and reliability in these advanced network infrastructures.

关键词： 6G mobile communication Performance evaluation Vehicular and wireless technologies Technological innovation Refining Open RAN Handover Reliability Vehicle dynamics Testing

来源：评论

学校读者我要写书评

暂无评论

G-Mix: A Generalized Mixup Learning Framework Towards Flat Minima

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Li, Xingyu Tang, Bo Mississippi State University Department of Electrical and Computer Engineering Mississippi StateMS39762 United States Worcester Polytechnic Instiute Department of Electrical and Computer Engineering WorcesterMA United States

Deep neural networks (DNNs) have demonstrated promising results in various complex tasks. However, such DNN models face challenges related to over-parameterization, particularly in scenarios where training data is scarce. In response to these challenges and to improve the generalization capabilities of DNNs, the Mixup technique has emerged, which effectively addresses the limitations posed by over-parameterization. Nevertheless, it still produces suboptimal outcomes. Inspired by the successful Sharpness-Aware Minimization (SAM) method, which establishes a connection between the sharpness of the training loss landscape and model generalization, we propose a new learning framework called Generalized-Mixup, which combines the strengths of Mixup and SAM for training DNN models. The theoretical analysis provided demonstrates how the developed G-Mix framework enhances generalization. Additionally, to further optimize DNN performance with the G-Mix framework, we introduce two novel algorithms: Binary G-Mix (BG-Mix) and Decomposed G-Mix (DG-Mix). These algorithms partition the training data into two subsets based on the sharpness-sensitivity of each example to address the issue of "manifold intrusion"in Mixup. Both theoretical explanations and experimental results reveal that the proposed BG-Mix and DG-Mix algorithms further enhance model generalization across multiple datasets and models, achieving state-of-the-art performance. © 2020 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Additively Manufactured Receiver Design for Wirelessly-Powered Biomedical Applications

Additively Manufactured Receiver Design for Wirelessly-Power...

引用

IEEE Biomedical Circuits and Systems (BIOCAS)

作者： Amin Hazrati Marangalou Miguel Arturo Gonzalez Ulkuhan Guler Department of Electrical and Computer Engineering Worcester Polytechnic Institute Worcester MA USA

This paper presents a miniaturized receiver prototype fabricated using an additive manufacturing electronics process. We aim to demonstrate the feasibility and advantages of using additive manufacturing for embedding the essential components of an inductive link in a compact form factor for miniaturized biomedical devices. We demonstrated various geometries of planar and helical coils, with average diameters of 20 mm. The wireless power transfer system comprises a class-E power amplifier operating at 6.78 MHz, a 10 µH transmitter coil, and a full-wave active rectifier fabricated in TSMC 180 nm CMOS process technology. The power delivered to a 500 Ω load at the output of the active rectifier varies from 2.7 mW to 42 mW for planar coils and 3 mW to 45 mW for helical coils, over a range of 1 cm to 4 cm. The transmitter’s power consumption is kept constant at 1.25 W throughout the experiments. Furthermore, in the case of helical coils, a lateral center-to-center misalignment of 1 cm at a distance of 2 cm between the receiver and transmitter results in a 10 mW drop in the output power.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Career-Based Explainable Course Recommendation 18th

Career-Based Explainable Course Recommendation

引用

18th International Conference on Information for a Better World: Normality, Virtuality, Physicality, Inclusivity, iConference 2023

作者： Striebel, Jacob Myers, Rebecca Liu, Xiaozhong Luddy School of Informatics Computing and Engineering Indiana University BloomingtonIN47408 United States Department of Computer Science Worcester Polytechnic Institute WorcesterMA01609 United States

ISBN: (纸本)9783031280313

The type and quality of education that a student receives can have a profound impact on their career. In contrast to education that is not intentionally organized to help students achieve specific career objectives, career-based education seeks to provide students with the skills that are required to achieve specific career goals. In this work, we propose a course recommendation framework that is designed to recommend courses based directly on their ability to teach skills relevant to a user-specified career goal. Within our framework, course recommendations are generated in a transparent manner, using skills to bridge between jobs and courses in a knowledge-based inference procedure. Due to the procedure’s transparency, our system is able to provide faithful template-based explanations detailing why each recommended course was chosen for recommendation. Our framework contrasts with other course recommendation systems in the literature that lack the ability to explain their choices and therefore may lack trustworthiness from the perspective of a user. The proposed framework has several applications, including assisting students with course planning, as well as aiding with curriculum evaluation and development by providing insight into the usefulness of specific courses to specific careers. We conduct a preliminary evaluation of our system, and its performance is competitive against two baselines. We provide all the resources needed to reproduce our results. (http://***/striebel/cbecr ) © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Lessons on mobile apps for COVID-19 from China

引用

Journal of Safety Science and Resilience 2021年第2期2卷 40-49页

作者： Sophia L.Zhou Xianhan Jia Samuel P.Skinner William Yang Isabelle Claude Mass Academy of Math and Science Worcester Polytechnic Institute85 Prescott StreetWorcesterMA 01605United States Department of Computer Science Worcester Polytechnic Institute100 Institute RoadWorcesterMA 01609United States Department of Physics Worcester Polythenic Institute100 Institute RoadWorcesterMA 01609United States Department of Biomedical Engineering Worcester Polytechnic Institute100 Institute RoadWorcesterMA 10609United States

The COVID-19 pandemic has impacted the global society and human life *** countries have launched COVID-19 mobile apps with a wide range in how these apps *** it is hoped that these apps can assist in the fight against COVID-19,many are worried about user *** implemented“health code”systems,which assigned neighborhoods and citizens a specific health code,meant to indicate their risk of having been exposed to *** most widely used health code systems were hosted on the popular apps WeChat and Alipay,each with billions of *** experts argued that China’s use of mobile applications was essential to its successful combat against *** in this study are a summary of mobile technology usage in China,a review of previous studies of mobile technology in healthcare,and a brief survey of some existing mobile applications for COVID-19 that were *** included are outcomes of interviews with healthcare and public safety experts and a public survey to understand how mobile applications were used in China’s response to *** interviews revealed four important themes:personal privacy,community involvement,government involvement,and situational *** was found that a key concern was maintaining a balance between collecting and utilizing personal information,as well as protecting this *** addition,close collaboration between local communities and the national government was *** applications assisted in communication and coordination but did not replace the work of people such as delivery drivers and contact *** results also showed that there was room for improvement,especially accessibility for the elderly or those unfamiliar with *** results were obtained from our *** was interesting to find that the apps were mostly used for“accessing information on COVID-19.”In addition,respondents overwhelmingly identified“information”as the most valuable featur

关键词： Mobile apps COVID-19 response Survey Interview Lessons

来源：评论

学校读者我要写书评

暂无评论

Thermal Ablation Therapy Control with Tissue Necrosis-driven Temperature Feedback Enabled by Neural State Space Model with Extended Kalman Filter

Thermal Ablation Therapy Control with Tissue Necrosis-driven...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Ryo Murakami Satoshi Mori Haichong K. Zhang Department of Robotics Engineering Worcester Polytechnic Institute Worcester MA The United States Department of Biomedical Engineering Robotics Engineering and Computer Science Engineering Worcester Polytechnic Institute Worcester MA The United States

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Thermal ablation therapy is a major minimally invasive treatment. One of the challenges is that the targeted region and therapeutic progression are often invisible to clinicians, requiring feedback provided in numerical information or imaging. Several emerging imaging modalities offer visualization of the ablation-induced necrosis formation; however, relying solely on necrosis monitoring can result in tissue overheating and endangering patients. Some of the necrosis monitoring modalities are known for their capabilities in temperature sensing, but the principles on which they are based have several limitations, such as sensitivity to the tissue motion and their environment. In this study, we propose a necrosis progression-based temperature estimation technique as an added safety feature for avoiding overheating. This model-based method does not require additional sensing hardware. It is designed to work as an independent estimator or a complimentary estimation component with other thermometers for improved robustness. For this objective, the Neural State Space model is used to approximate the ablation therapy, whose theoretical models involve nonlinear partial differential equations. Then, the Extended Kalman Filter is designed based on the model. The simulation study shows the estimation module robustly estimates the tissue temperature under several types of noise. The maximum estimation error observed before terminating ablation was around 1 °C, and the desired safety feature was successfully demonstrated. The estimator is expected to be used in a variety of necrosis monitoring modalities to guarantee more precise and safer treatment. More ambitiously, the architecture with the Neural State Space model and Extended Kalman Filter is generalizable to other medical/biological procedures involving nonlinear and patient/environment-specific physics and even to procedures having no reliable theoretical models.

关键词： Thermometers Estimation Medical treatment Mathematical models Robustness Sensors Safety Temperature control Kalman filters Monitoring

来源：评论

学校读者我要写书评

暂无评论

Calibratable Polymorphic Temperature Sensor for Detecting Fault Injection and Side-Channel Attacks

Calibratable Polymorphic Temperature Sensor for Detecting Fa...

引用

IEEE International Workshop on Hardware-Oriented Security and Trust (HOST)

作者： Tasnuva Farheen Sourav Roy Jia Di Shahin Tajik Domenic Forte Department of Electrical and Computer Engineering University of Florida Department of Electrical and Computer Engineering University of Arkansas Department of Electrical and Computer Engineering Worcester Polytechnic Institute

ISBN: (数字)9798350373943

ISBN: (纸本)9798350373950

Security of a computing system can be compromised by physical attacks against the hardware. Side-channel attacks involve the observation of integrated circuit (IC) or system behavior to extract assets such as cryptographic keys. Fault injection attacks involve the manipulation of underlying circuits to provoke erroneous operations that lead to the escalation of privilege or leakage of secret information. Some side-channel and fault injection attacks force circuits to work at temperatures out of operating range. Several countermeasures have been proposed to detect temperature change. However, they do not perform well in wide temperature fluctuations, have a large overhead area, or introduce other reliability concerns. This paper proposes a calibratable Null Convention Logic-based (NCL) polymorphic sensor that changes its functionality with temperature and can sense whether the temperature goes below or above a carefully designed application-specific threshold. It can be used with a wide range of process technologies without requiring significant modification. Low area overhead, low power consumption, configurable nature, and easy integration make it ideal for ICs. Our results show that this sensor can work at various temperature ranges with reliable operation with ± 1 0 C confidence, 8 μm 2 area and 19.2 μW power overhead, which is approximately 40 $x$ less overhead compared to alternative techniques.

关键词： Temperature sensors Integrated circuits Temperature distribution Power demand Fluctuations Force Side-channel attacks

来源：评论

学校读者我要写书评

暂无评论

Review of In-Pixel Gain Amplifiers and Readout Circuits for Low-Light CMOS Image Sensors

IEEE Sensors Reviews

引用

IEEE Sensors Reviews 2025年 2卷 95-111页

作者： Amr M. Maghraby Ibrahim Bozyel Islam T. Abougindia Suat U. Ay Electrical and Computer Engineering Department University of Idaho Moscow ID USA Electrical and Computer Engineering Department Worcester Polytechnique Institute Worcester MA USA Electronics Engineering Department Military Technical College Cairo Egypt

The low-light performance of image sensors can be enhanced by designing high-effective conversion gain signal paths from photon conversion sites to chip outputs. This can be achieved by using high-gain in-pixel amplifiers, high-gain column amplifiers, and by reducing the conversion capacitance of photon-sensing nodes. However, each of these approaches presents unique challenges and limitations that have restricted their widespread adoption in low-light applications. This article reviews the use of in-pixel gain amplifiers and their signal chain electronics in high-conversion-gain complementary metal–oxide–semiconductor (CMOS) image sensors over the past two decades. In-pixel gain amplifiers are classified into different categories according to the type of amplification technique used. Analyses of the column-referred conversion gain and the noise of each topology are presented alongside the different metrics used to characterize CMOS image sensor pixels for low-light imaging applications. The performance metrics of various in-pixel gain amplifiers are compared, providing a framework that highlights the best achieved input-referred noise in CMOS image sensors over the past 15 years. Furthermore, different tradeoffs are examined between optimizing conversion gain, pixel full-well capacity, and input read noise in both voltage and charge domains.

关键词： Noise Voltage Transistors Topology CMOS image sensors Reviews Imaging Capacitance Transconductors Circuits

来源：评论

学校读者我要写书评

暂无评论

WIP: Federated Learning for Routing in Swarm Based Distributed Multi-Hop Networks

arXiv

引用

arXiv 2023年

作者： Cash, Martha Murphy, Joseph Wyglinski, Alexander Department of Electrical and Computer Engineering Worcester Polytechnic Institute WorcesterMA United States

Unmanned Aerial Vehicles (UAVs) are a rapidly emerging technology offering fast and cost-effective solutions for many areas, including public safety, surveillance, and wireless networks. However, due to the highly dynamic network topology of UAVs, traditional mesh networking protocols, such as the Better Approach to Mobile Ad-hoc Networking (B.A.T.M.A.N.), are unsuitable. To this end, we investigate modifying the B.A.T.M.A.N. routing protocol with a machine learning (ML) model and propose implementing this solution using federated learning (FL). This work aims to aid the routing protocol to learn to predict future network topologies and preemptively make routing decisions to minimize network congestion. We also present an FL testbed built on a network emulator for future testing of the proposed ML aided B.A.T.M.A.N. routing protocol. © 2023, CC BY.

关键词： Machine 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：