检索结果-内蒙古大学图书馆

2022 Compound Semiconductor Week, CSW 2022

作者： Li, Kexin Rakheja, Shaloo University of Illinois at Urbana-Champaign Holonyak Micro and Nanotechnology Laboratory Department of Electrical and Computer Engineering 208 N. Wright St. UrbanaIL61801 United States

ISBN: (数字)9781665453400

ISBN: (纸本)9781665453400

This abstract presents a physical model to describe the current-voltage response of quasi-ballistic GaN HEMTs operating at ultra-low temperatures up to the cryogenic limit (4.2 K). The model includes various sources of carrier scatterings, such as due to interface roughness and phonons, as well as the temperature-dependent thermal conductivity of the heterostructure to make realistic assessments of the merits of GaN technology at ultra-low temperatures. The model is validated in the temperature range of 77 K to 300 K using a judicious mix of measurement data and technology computer-aided design (TCAD) simulations. The model is further applied to predict the device's I-V curves, transconductance, and cut-off frequency at 4.2 K over a broad bias range. The model presented here offers critical insights into the role of temperature and heterostructure design of GaN HEMTs when used in an extremely low-temperature environment. Additionally, the model can be integrated into a circuit simulation framework to facilitate the design of cryogenic GaN-based control circuitry that can be interfaced with quantum computing hardware. © 2022 IEEE.

关键词： Cryogenics

来源：评论

学校读者我要写书评

暂无评论

On the generalization of stochastic gradient descent with momentum

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 1132-1187页

作者： Ali Ramezani-Kebrya Kimon Antonakopoulos Volkan Cevher Ashish Khisti Ben Liang Department of Informatics University of Oslo and Visual Intelligence Centre Integreat Norwegian Centre for Knowledge-driven Machine Learning Oslo Norway Laboratory for Information and Inference Systems (LIONS) EPFL EPFL STI IEL LIONS Lausanne Switzerland Department of Electrical and Computer Engineering University of Toronto Toronto ON Canada

While momentum-based accelerated variants of stochastic gradient descent (SGD) are widely used when training machine learning models, there is little theoretical understanding on the generalization error of such methods. In this work, we first show that there exists a convex loss function for which the stability gap for multiple epochs of SGD with standard heavy-ball momentum (SGDM) becomes unbounded. Then, for smooth Lipschitz loss functions, we analyze a profiles momentum-based update rule, i.e., SGD with early momentum (SGDEM) under a broad range of step-sizes, and show that it can train machine learning models for multiple epochs with a guarantee for generalization. Finally, for the special case of strongly convex loss functions, we find a range of momentum such that multiple epochs of standard SGDM, as a special form of SGDEM, also generalizes. Extending our results on generalization, we also develop an upper bound on the expected true risk, in terms of the number of training steps, sample size, and momentum. Our experimental evaluations verify the consistency between the numerical results and our theoretical bounds. SGDEM improves the generalization error of SGDM when training ResNet-18 on ImageNet in practical distributed settings.

关键词： uniform stability generalization error heavy-ball momentum stochastic gradient descent non-convex

来源：评论

学校读者我要写书评

暂无评论

Flight Risk Assessment of Urban Air Mobility Vehicles and Routes Based on Battery Energy Consumption

Flight Risk Assessment of Urban Air Mobility Vehicles and Ro...

引用

Conference on Digital Avionics systems (DASC)

作者： Yonas Ayalew Abdul-Rauf Nuhu Lydia Zeleke Vahid Hemmati Abdollah Homaifar Edward Tunstel Department of Electrical and Computer Engineering North Carolina A&T State University NC USA Motiv Space Systems Inc. Pasadena CA USA

ISBN: (数字)9798350349610

ISBN: (纸本)9798350349627

This paper presents a flight risk assessment framework for Urban Air Mobility (UAM) vehicles and routes. It considers separation automation and mission structure sensitivity based on energy demand. We evaluate the energy consumption of a conceptual hexacopter electric Vertical Takeoff and Landing (eVTOL) vehicle for identified potential UAM routes from Dallas-Fort Worth and San Francisco metropolitan regions considering level flight conflict management. A mission structure-based parameter sensitivity study is conducted for operational flexibility, and assessment of associated risk level, of the UAM vehicle's flight energy consumption using Conditional Value at Risk (CVaR) statistical metrics. Our results demonstrate that the feasibility and energy demand of the flights can be affected greatly by the vehicle configuration, range of the operational routes, aircraft density in the airspace, conflicts, and different parameter values of the mission structure. This study high-lights the fact that a mission parameter-based energy demand evaluation that considers performance-based energy reserve can provide information about possible vehicle capabilities in a specific operation. Additionally, the CVaR metric captured the maximum level of risk associated with high energy-demanding flights for the potential routes in the two metropolitan regions. These findings provide air transportation decision-makers with crucial insights for enhancing strategies aimed at accelerating the design-to-certification process of UAM vehicles and mitigating operational hazards.

关键词： Energy consumption Reactive power Sensitivity Urban areas Probability Hazards Risk management Aircraft Payloads Guidelines

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Tube-based Control Synthesis of Stochastic Multi-Agent systems under Signal Temporal Logic

arXiv

引用

arXiv 2024年

作者： Vlahakis, Eleftherios E. Lindemann, Lars Sopasakis, Pantelis Dimarogonas, Dimos V. Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm10044 Sweden Thomas Lord Department of Computer Science Viterbi School of Engineering University of Southern California Los AngelesCA90089 United States School of Electronics Electrical Engineering and Computer Science Queen’s University Northern Ireland Belfast United Kingdom

We consider the control design of stochastic discrete-time linear multi-agent systems (MASs) under a global signal temporal logic (STL) specification to be satisfied at a predefined probability. By decomposing the dynamics into deterministic and error components, we construct a probabilistic reachable tube (PRT) as the Cartesian product of reachable sets of the individual error systems driven by disturbances lying in confidence regions (CRs) with a fixed probability. By bounding the PRT probability with the specification probability, we tighten all state constraints induced by the STL specification by solving tractable optimization problems over segments of the PRT, and relax the underlying stochastic problem with a deterministic one. This approach reduces conservatism compared to tightening guided by the STL structure. Additionally, we propose a recursively feasible algorithm to attack the resulting problem by decomposing it into agent-level subproblems, which are solved iteratively according to a scheduling policy. We demonstrate our method on a ten-agent system, where existing approaches are impractical. © 2024, CC BY.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

PathFormer: A Transformer-Based Framework for Vision-Centric Autonomous Navigation in Off-Road Environments

PathFormer: A Transformer-Based Framework for Vision-Centric...

引用

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

作者： Bilal Hassan Nadya Abdel Madjid Fatima Kashwani Mohamad Alansari Majid Khonji Jorge Dias Khalifa University Center for Autonomous Robotic Systems (KUCARS) Abu Dhabi UAE Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi UAE

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

The efficient navigation of autonomous vehicles across rugged and unstructured terrains remains a significant challenge. Most existing research in this area emphasizes the need for complex mappings or intricate multi-step methodologies. However, these traditional approaches often struggle to adapt to dynamic changes in environmental conditions. In this paper, we introduce PathFormer, an end-to-end framework designed specifically to address these challenges. PathFormer utilizes transformers to decode free-space semantics and configurations directly from camera images, enabling efficient path planning without the reliance on detailed, pre-existing maps. The performance of PathFormer was rigorously evaluated across diverse datasets, where it demonstrated superior capabilities, outperforming other state-of-the-art methods by 3.68% in precisely segmenting free-space regions and showing a 13.65% improvement in correctly predicting traversable paths.

关键词： Visualization Image segmentation Navigation Semantics Transformers Robustness Path planning Vehicle dynamics Autonomous vehicles Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Empowering Patient Care: A Novel Patient Drug Recommendation System Using Artificial Intelligence with Modified Learning Strategy 1

Empowering Patient Care: A Novel Patient Drug Recommendation...

引用

1st IEEE International Conference on Computing and Data Science, ICCDS 2024

作者： Samuthira Pandi, V. Kavitha, V.R. Shinev, S. Arumai Roopa Chandrika, R. Valarmathy, A.S. Glory, E. Centre for Advanced Wireless Integrated Technology Chennai Institute of Technology Tamil Nadu Chennai India R.M.K. Engineering College Department of Computer Science and Business Systems Tamil Nadu Chennai India S A Engineering College Department of CSE Tamil Nadu Chennai India Karpagam Academy of Higher Education Department of CSE TamilNadu Coimbatore India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electrical and Electronics Engineering Tamil Nadu Chennai India Saveetha University Department of Biosciences Chennai India

ISBN: (纸本)9798350365337

In the era of personalized medicine, the demand for efficient and accurate drug recommendation systems has escalated. This paper introduces a pioneering approach to enhance patient care through a novel Patient Drug Recommendation System (PDRS). Leveraging the power of machine learning (ML), specifically Cascaded Multi-Layer Perceptrons (MLP), our system aims to provide precise and personalized drug recommendations based on an extensive Drug Review Dataset. The proposed PDRS capitalizes on the inherent complexities of drug reviews, extracting valuable insights and patterns from patient feedback. The cascaded MLP architecture is designed to sequentially process and analyze diverse aspects of drug reviews, capturing nuanced information and correlations that may be overlooked by traditional recommendation systems. Our methodology involves preprocessing the drug review dataset to address noise and ensure data quality. Feature extraction techniques are applied to distill meaningful information, and the cascaded MLP model is trained using a robust set of labeled data. The system's performance is evaluated on various metrics, with a remarkable accuracy of 97%, signifying its efficacy in predicting suitable drug recommendations for patients. The cascaded MLP architecture demonstrates superior adaptability, allowing the system to comprehend intricate relationships between patients, drugs, and their respective effects. The achieved accuracy underscores the potential of our PDRS to revolutionize clinical decision-making, fostering a more personalized and efficient approach to prescribing medications. © 2024 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization for Cooperative Service-Caching, Computation-Offloading, and Resource-Allocations Over EH/MEC-Based Ultra-Dense Mobile Networks

Joint Optimization for Cooperative Service-Caching, Computat...

引用

IEEE International Conference on Communications (ICC)

作者： Zhian Chen Fei Wang Xi Zhang College of Electronic and Information Engineering Southwest University Chongqing China Department of Electrical and Computer Engineering Networking and Information Systems Laboratory Texas A&M University College Station TX USA

Mobile edge-computing (MEC) enabled ultra-dense networks (UDNs), which merges edge-computing with UDNs, can provide enormous benefits, e.g., ultra-low latency. However, due to the ultra-dense deployment of small-cell base stations (SBSs), it becomes infeasible to just depend on the grid power for energy providing, and also it is challenging to jointly optimize service-caching, computation-offloading, and resource-allocation. Integrating energy-harvesting (EH) techniques into MEC-enabled UDNs, we investigate the joint optimization for cooperative service-caching, computation-offloading, and resource-allocation. In our considered UDNs, there exist a large number of EH-based mobile users (MUs) and a mixture of on-grid SBSs, powered by electric grid, and off-grid SBSs, powered by solar, radio frequency (RF) energy, etc. We formulate an energy minimization problem to minimize the sum of weighted energy consumption of all MUs and off-grid SBSs. Also, we develop a two-timescale based joint cooperative service-caching, computation-offloading, and resource-allocation scheme based on the hierarchical multiagent deep reinforcement learning (HMDRL). Using HMDRL, we first derive SBSs' cooperative service-caching policies which are updated in each time frame consisting of multiple time slots. Then, we derive MUs' and SBSs' computation-offloading policies and SBSs' computation resource-allocation policies, which are updated in each time slot. Finally, we validate and evaluate the performances of our proposed schemes through simulations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neuromorphic Chiplet Architecture for Wide Area Motion Imagery Processing

Neuromorphic Chiplet Architecture for Wide Area Motion Image...

引用

Argentine Conference on Electronics (CAE)

作者： Andreas G. Andreou Tomas Figliolia Kayode Sanni Thomas S. Murray Gaspar Tognetti Daniel R. Mendat Jamal L. Molin Martin Villemur Philippe O. Pouliquen Pedro Julian Ralph Etienne-Cummings Isidoros Doxas Department of Electrical and Computer Engineering Johns Hopkins University Baltimore MD work performed while at Johns Hopkins University work performed while at BAE Systems

We present the system architecture for real-time processing of data that originates in large format tiled imaging arrays used in wide area motion imagery ubiquitous surveillance. High performance and high throughput is achieved through approximate computing and fixed point variable precision (6 bits to 18 bits) arithmetic. The architecture implements a variety of processing algorithms in what we consider today as Third Wave AI and Machine Intelligence ranging from convolutional networks (CNNs) to linear and non-linear morphological processing, probabilistic inference using exact and approximate Bayesian methods and Deep Neural Networks based classification. The processing pipeline is implemented entirely using event based neuromorphic and stochastic computational primitives. An emulation of the system architecture demonstrated processing in real-time 160 x 120 raw pixel data running on a reconfigurable computing platform (5 Xilinx Kintex-7 FPGAs). The reconfigurable computing implementation was developed to emulate the computational structures for a 2.5D System chiplet design, that was fabricated in the 55nm GF CMOS technology. To optimize for energy efficiency of a mixed level system, a general energy aware methodology is applied through the design process at all levels from algorithms and architecture all the way down to technology and devices, while at the same time keeping the operational requirements and specifications for the task at focus.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TerrainSense: Vision-Driven Mapless Navigation for Unstructured Off-Road Environments

TerrainSense: Vision-Driven Mapless Navigation for Unstructu...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Bilal Hassan Arjun Sharma Nadya Abdel Madjid Majid Khonji Jorge Dias Khalifa University Center for Autonomous Robotic Systems (KUCARS) Abu Dhabi UAE Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi UAE

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Navigating autonomous vehicles efficiently across unstructured and off-road terrains remains a formidable challenge, often requiring intricate mapping or multi-step pipelines. However, these conventional approaches struggle to adapt to dynamic environments. This paper presents TerrainSense, an end-to-end framework that overcomes these limitations. By utilizing a transformers, TerrainSense detects lane semantics and topology from camera images, enabling mapless path planning without the reliance on highly detailed maps. The efficacy of TerrainSense was rigorously assessed on six diverse datasets, evaluating its efficacy in detection, segmentation, and path prediction using various metrics. Notably, it outperforms the other state-of-the-art methods by 9.32% in precisely predicting the path with 18.28% faster inference time.

关键词： Navigation Semantics Pipelines Transformers Robustness Path planning Topology

来源：评论

学校读者我要写书评

暂无评论

FIXED-BUDGET DIFFERENTIALLY PRIVATE BEST ARM IDENTIFICATION

arXiv

引用

arXiv 2024年

作者： Chen, Zhirui Karthik, P.N. Chee, Yeow Meng Tan, Vincent Y.F. The Department of Industrial Systems Engineering and Management National University of Singapore Singapore The Institute of Data Science National University of Singapore Singapore The Department of Mathematics The Department of Electrical and Computer Engineering National University of Singapore Singapore

We study best arm identification (BAI) in linear bandits in the fixed-budget regime under differential privacy constraints, when the arm rewards are supported on the unit interval. Given a finite budget T and a privacy parameter Ε > 0, the goal is to minimise the error probability in finding the arm with the largest mean after T sampling rounds, subject to the constraint that the policy of the decision maker satisfies a certain Ε-differential privacy (Ε-DP) constraint. We construct a policy satisfying the Ε-DP constraint (called DP-BAI) by proposing the principle of maximum absolute determinants, and derive an upper bound on its error probability. Furthermore, we derive a minimax lower bound on the error probability, and demonstrate that the lower and the upper bounds decay exponentially in T, with exponents in the two bounds matching order-wise in (a) the sub-optimality gaps of the arms, (b) Ε, and (c) the problem complexity that is expressible as the sum of two terms, one characterising the complexity of standard fixed-budget BAI (without privacy constraints), and the other accounting for the Ε-DP constraint. Additionally, we present some auxiliary results that contribute to the derivation of the lower bound on the error probability. These results, we posit, may be of independent interest and could prove instrumental in proving lower bounds on error probabilities in several other bandit problems. Whereas prior works provide results for BAI in the fixed-budget regime without privacy constraints or in the fixed-confidence regime with privacy constraints, our work fills the gap in the literature by providing the results for BAI in the fixed-budget regime under the Ε-DP constraint. Copyright © 2024, The Authors. All rights reserved.

关键词： Decision making

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：