检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Tan, Shengbo Zhang, Zeyu Cai, Ying Ergu, Daji Wu, Lin Hu, Binbin Yu, Pengzhang Zhao, Yang Key Laboratory of Electronic Information Engineering College of Electronic and Information Southwest Minzu University Chengdu610225 China College of Engineering Computing and Cybernetics The Australian National University CanberraACT2601 Australia Hunan University of Technology Zhuzhou410072 China Department of Computer Science and Information Technology La Trobe University BundooraVIC3086 Australia

Medical imaging segmentation plays a significant role in the automatic recognition and analysis of lesions. State-of-the-art methods, particularly those utilizing transformers, have been prominently adopted in 3D semantic segmentation due to their superior performance in scalability and generalizability. However, plain vision transformers encounter challenges due to their neglect of local features and their high computational complexity. To address these challenges, we introduce three key contributions: Firstly, we proposed SegStitch, an innovative architecture that integrates transformers with denoising ODE blocks. Instead of taking whole 3D volumes as inputs, we adapt axial patches and customize patch-wise queries to ensure semantic consistency. Additionally, we conducted extensive experiments on the BTCV and ACDC datasets, achieving improvements up to 11.48% and 6.71% respectively in mDSC, compared to state-of-the-art methods. lastly, our proposed method demonstrates outstanding efficiency, reducing the number of parameters by 36.7% and the number of FLOPS by 10.7% compared to UNETR. This advancement holds promising potential for adapting our method to real-world clinical practice. The code will be available at https://***/goblin327/SegStitch. © 2024, CC BY-NC-SA.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A Classification of Cross-layer Optimization Approaches in LoRaWAN for Internet of Things

A Classification of Cross-Layer Optimization Approaches in L...

引用

International Conference on Ubiquitous and Future Networks, ICUFN

作者： Carl Christian Chaguile Melchizedek Alipio Miroslav Bures Department of Electronics and Computer Engineering De La Salle University 2401 Taft Avenue Malate Manila Philippines Department of Computer Science FEE Czech Technical University in Prague Karlovo namesti 13 Prague 2 Czechia

The Internet of Things (IoT) uses Low-Power Wide Area Networks (LPWAN) for applications that require long-range, energy-efficient, and low-cost end devices. LoRaWAN is one of the most popular LPWAN technologies because of its key features and openness making it highly suitable for IoT. Despite its exceptional features, some challenges faced by this technology are optimizing the protocol used for scheduling, low data rate, and duty cycle restrictions. One possible way to address these challenges is by using cross-layer optimization. This optimization technique violates the restrictions of the traditional OSI protocol stack giving freedom to its protocol layers. However, there is currently no summary of cross-layer methods implemented in LoRaWAN. This paper presents a classification of state-of-the-art cross-layer approaches that were used in optimizing the LoRaWAN technology in IoT. The cross-layer techniques were classified based on the merging of adjacent layers, direct communication between layers, and completely new abstractions. In addition, this paper identified the issues and challenges featured in these state-of-the-art cross-layer approaches. Finally, this paper serves as an overview of the performance of cross-layer optimization in LoRaWAN technology for IoT applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

UMS: Live Migration of Containerized Services across Autonomous Computing Systems

UMS: Live Migration of Containerized Services across Autonom...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Thanawat Chanikaphon Mohsen Amini Salehi HPCC Lab School of Computing and Informatics University of Louisiana at Lafayette LA USA Computer Science and Engineering Department HPCC Lab University of North Texas

Containerized services deployed within various computing systems, such as edge and cloud, desire live migration support to enable user mobility, elasticity, and load balancing. To enable such a ubiquitous and efficient service migration, a live migration solution needs to handle circumstances where users have various authority levels (full control, limited control, or no control) over the underlying computing systems. Supporting the live migration at these levels serves as the cornerstone of interoperability, and can unlock several use cases across various forms of distributed systems. As such, in this study, we develop a ubiquitous migration solution (called UMS) that, for a given containerized service, can automatically identify the feasible migration approach, and then seamlessly perform the migration across autonomous computing systems. UMS does not interfere with the way the orchestrator handles containers and can coordinate the migration without the orchestrator involvement. Moreover, UMS is orchestrator-agnostic, i.e., it can be plugged into any underlying orchestrator platform. UMS is equipped with novel methods that can coordinate and perform the live migration at the orchestrator, container, and service levels. Experimental results show that for single-process containers, the service-level approach, and for multi-process containers with small $(< 128 \mathbf{MiB})$ memory footprint, the container-level migration approach lead to the lowest migration overhead and service downtime. To demonstrate the potential of UMS in realizing interoperability and multi-cloud scenarios, we examined it to perform live service migration across heterogeneous orchestrators, and between Microsoft Azure and Google Cloud.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Effect of Underlap with Fixed Gate Length: GaN-Based Double-Gate MOSFETs 2

Effect of Underlap with Fixed Gate Length: GaN-Based Double-...

引用

2nd International Conference on Robotics, Electrical and Signal Processing Techniques, ICREST 2021

作者： Hasan, Md. Rokib Islam, Md. Rabiul Bhuiyan, Tanjim Masroor Nibir, Muhib Ashraf Hasan, Md. Emran Hossain, Tanvir American International University Dept. of Electrical and Electronic Engineering Dhaka Bangladesh Deakin University Dept. Electrical and Renewable Engineering Melbourne Australia City University Dept of Computer Science and Engineering Dhaka Bangladesh La Trobe University School of Engineering and Mathematical Science Melbourne Australia

ISBN: (纸本)9781665415767

The effect of gate length 8 nm with underlap of double-gate MOSFET has been designed for VLSI Technology. The evaluation process was followed by NEGF (non-equilibrium Green's function) formalism using SILVACO ATlaS followed to ITRS-2013. The investigations on the threshold voltage, Subthreshold Slope, ION, I_{OFF}, I_{ON}/I_{OFF}, DIBL, and switching characteristics of the electric field have been done with the simulation results. In the simulation, adopting symmetrical distances from the source to gate and gate to drain (S-G and G-D) by fixing the gate length identical are cited as underlap. Here, the observation has been done for LUN =(0 to 4 nm) underlap length. GaN and HfO2 have been chosen as channel material and dielectric material, respectively. The Proposed device structure indicates that GaN-based DG-MOSFETs for L_{G}=S nm with various underlap lengths is a promising candidate for the aspect of modern VLSI applications. © 2021 IEEE.

关键词： MOSFET devices

来源：评论

学校读者我要写书评

暂无评论

Phenotype Based Surrogate-Assisted Multi-objective Genetic Programming with Brood Recombination for Dynamic Flexible Job Shop Scheduling

Phenotype Based Surrogate-Assisted Multi-objective Genetic P...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Fangfang Zhang Yi Mei Su Nguyen Mengjie Zhang School of Engineering and Computer Science Victoria University of Wellington New Zealand Centre for Data Analytics and Cognition La Trobe University Melbourne Victoria Australia

ISBN: (纸本)9781665487696

Dynamic flexible job shop scheduling (DFJSS) is an important combinatorial optimisation problem with a large number of real-world applications such as component production in manufacturing. Genetic programming (GP), as a hyper-heuristic approach, has been widely used to learn scheduling heuristics for DFJSS. Brood recombination has been shown its effectiveness to improve the performance of GP by generating more offspring and preselecting only promising individuals into the next generation. However, evaluating more individuals requires more computational cost. Phenotype based surrogate models have been successfully used with GP to speed up the evaluation in single-objective dynamic job shop scheduling. However, its effectiveness on multi-objective dynamic job shop scheduling is unknown. To fill this gap, this paper proposes a novel surrogate-assisted multi-objective GP based on the phenotype of GP individuals for DFJSS. Specifically, we first use phenotypic vector to represent the behaviour of GP individuals in DFJSS. Second, K-nearest neighbour based surrogates are built according to the phenotypic characterisations and multiple fitness values of the evaluated individuals. last, the built surrogate models are used to predict the fitness of newly generated offspring in GP with brood recombination. The results show that with the same training time, the proposed algorithm can achieve significantly better scheduling heuristics than the compared algorithm. The analyses of population diversity, feature importance, and the number of non-dominated individuals have also shown the effectiveness of the proposed algorithm in different aspects.

关键词： Training Job shop scheduling Processor scheduling Heuristic algorithms Sociology Genetic programming Production

来源：评论

学校读者我要写书评

暂无评论

Towards a fully autonomous robotic system for detection and removal of surface defects in fiber glass panels

引用

IFAC-PapersOnLine 2022年第15期55卷 129-135页

作者： James Oubre William Ard Joshua Nguyen Corina Barbalata Electrical Engineering and Computer Science Department Louisiana State University Baton Rouge LA 70803 USA Mechanical and Industrial Engineering Department Louisiana State University Baton Rouge LA 70803 USA

Wind blades for turbines are commonly manufactured from fiber glass. A last step in the manufacturing process of such blades is sanding of the surface to remove defects that occur during the process. This paper presents an autonomous robotic system performing sanding operations for surface defect removal in fiber glass panels. The proposed approach uses a collaborative robotic system equipped with a vision system. Surface defects are detected using traditional computer vision algorithms and a path planning strategy is designed that solves multi-goal and coverage path planning problems. The robotic system equipped with a specialized end-effector will autonomously perform sanding of the defected areas using a constant velocity control system. Experimental results are evaluated based on the accuracy of the defect detection and roughness measurements before and after the sanding process has been completed.

关键词： intelligent systems automation robotic system computer vision cascade control

来源：评论

学校读者我要写书评

暂无评论

Successive Bayesian Reconstructor for FAS Channel Estimation

Successive Bayesian Reconstructor for FAS Channel Estimation

引用

IEEE Conference on Wireless Communications and Networking

作者： Zijian Zhang Jieao Zhu Linglong Dai Robert W. Heath Department of Electronic Engineering Tsinghua University Beijing China Beijing National Research Center for Information Science and Technology (BNRist) Beijing China Department of Electrical and Computer Engineering University of California San Diego La Jolla CA USA

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

Fluid antenna systems (FASs) can reconfigure their locations freely within a spatially continuous space. To keep favorable antenna positions, the channel state information (CSI) acquisition for FASs is essential. While some techniques have been proposed, most existing FAS channel estimators require several channel assumptions, such as slow variation and angular-domain sparsity. When these assumptions are not reasonable, the model mismatch may lead to unpredictable performance loss. In this paper, we propose the successive Bayesian reconstructor (S- BAR) as a general solution to estimate FAS channels. Unlike model-based estimators, the proposed S- BAR is prior-aided, which builds the experiential kernel for CSI acquisition. Inspired by Bayesian regression, the key idea of S- BAR is to model the FAS channels as a stochastic process, whose uncertainty can be successively eliminated by kernel-based sampling and regression. In this way, the predictive mean of the regressed stochastic process can be viewed as the maximum a posterior (MAP) estimator of FAS channels. Simulation results verify that, in both model-mismatched and model-matched cases, the proposed S-BAR can achieve higher estimation accuracy than the existing schemes.

关键词： Accuracy Uncertainty Simulation Channel estimation Stochastic processes Estimation Bayes methods

来源：评论

学校读者我要写书评

暂无评论

Detecting Generated Images by Real Images Only

arXiv

引用

arXiv 2023年

作者： Bi, Xiuli Liu, Bo Yang, Fan Xiao, Bin Li, Weisheng Huang, Gao Cosman, Pamela C. Department of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China Department of Automation Tsinghua University Beijing100084 China Department of Electrical and Computer Engineering University of California at San Diego La Jolla CA92093 United States

As deep learning technology continues to evolve, the images yielded by generative models are becoming more and more realistic, triggering people to question the authenticity of images. Existing generated image detection methods detect visual artifacts in generated images or learn discriminative features from both real and generated images by massive training. This learning paradigm will result in efficiency and generalization issues, making detection methods always lag behind generation methods. This paper approaches the generated image detection problem from a new perspective: Start from real images. By finding the commonality of real images and mapping them to a dense subspace in feature space, the goal is that generated images, regardless of their generative model, are then projected outside the subspace. As a result, images from different generative models can be detected, solving some long-existing problems in the field. Experimental results show that although our method was trained only by real images and uses 99.9% less training data than other deep learning-based methods, it can compete with state-of-the-art methods and shows excellent performance in detecting emerging generative models with high inference efficiency. Moreover, the proposed method shows robustness against various post-processing. These advantages allow the method to be used in real-world scenarios. Copyright © 2023, The Authors. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

A Control Approach for Nonlinear Stochastic State Uncertain Systems with Probabilistic Safety Guarantees

A Control Approach for Nonlinear Stochastic State Uncertain ...

引用

American Control Conference (ACC)

作者： Mohammad S. Ramadan Mohammad Alsuwaidan Ahmed Atallah Sylvia Herbert Mathematics and Computer Science Division Argonne National Laboratory Lemont IL USA Department of Mechanical and Aerospace Engineering University of California San Diego La Jolla CA USA

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

This paper presents an algorithm to apply nonlinear control design approaches to the case of stochastic systems with partial state observation. Deterministic nonlinear control approaches are formulated under the assumption of full state access and, often, relative degree one. We propose a control design approach that initially generates a control policy for nonlinear deterministic models with full state observation. The resulting control policy is then employed to construct an importance-like probability distribution over the space of control sequences which are to be evaluated for the true stochastic and state-uncertain dynamics. In the sampling step of a random search control optimization procedure, this distribution serves to focus the exploration effort on certain regions of the control space. The sampled control sequences are assigned costs determined by a prescribed finite-horizon performance and safety measure that considers stochastic dynamics. This sampling algorithm is parallelizable, exhibits computational complexity indifferent to the state dimension, and probabilistically guarantees safety over the prescribed prediction horizon. A numerical simulation is provided to compare the presented approach to the certainty equivalence controller.

关键词： Adaptation models Uncertain systems Monte Carlo methods Control design Stochastic systems Stochastic processes Aerospace electronics

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Replay Strategies for Continual Learning with Limited Data

Unsupervised Replay Strategies for Continual Learning with L...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Anthony Bazhenov Pahan Dewasurendra Giri P. Krishnan Jean Erik Delanois Del Norte High School San Diego CA USA Department of Medicine University of California San Diego La Jolla CA USA Department of Computer Science & Engineering University of California San Diego La Jolla CA USA

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Artificial neural networks (ANNs) show limited performance with scarce or imbalanced training data and face challenges with continuous learning, such as forgetting previously learned data after new tasks training. In contrast, the human brain can learn continuously and from just a few examples. This research explores the impact of ’sleep’ — an unsupervised phase incorporating stochastic network activation with local Hebbian learning rules — on ANNs trained incrementally with limited and imbalanced datasets, specifically MNIST and Fashion MNIST. We discovered that introducing a sleep phase significantly enhanced accuracy in models trained with limited data. When a few tasks were trained sequentially, sleep replay not only rescued previously learned information that had been forgotten following new task training but also often enhanced performance in prior tasks, especially those trained with limited data. This study highlights the multifaceted role of sleep replay in augmenting learning efficiency and facilitating continual learning in ANNs.

关键词： Training Continuing education Training data Stochastic processes Learning (artificial intelligence) Data models Task analysis

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：