检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Li, Mengke Hu, Zhikai Lu, Yang Lan, Weichao Cheung, Yiu-Ming Huang, Hui Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Computer Science Hong Kong Baptist University Hong Kong Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics Xiamen University Xiamen China

The imbalanced distribution of long-tailed data presents a considerable challenge for deep learning models, as it causes them to prioritize the accurate classification of head classes but largely disregard tail classes. The biased decision boundary caused by inadequate semantic information in tail classes is one of the key factors contributing to their low recognition accuracy. To rectify this issue, we propose to augment tail classes by grafting the diverse semantic information from head classes, referred to as head-to-tail fusion (H2T). We replace a portion of feature maps from tail classes with those belonging to head classes. These fused features substantially enhance the diversity of tail classes. Both theoretical analysis and practical experimentation demonstrate that H2T can contribute to a more optimized solution for the decision boundary. We seamlessly integrate H2T in the classifier adjustment stage, making it a plug-and-play module. Its simplicity and ease of implementation allow for smooth integration with existing long-tailed recognition methods, facilitating a further performance boost. Extensive experiments on various long-tailed benchmarks demonstrate the effectiveness of the proposed H2T. The source code is available at https://***/Keke921/H2T. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Learning-Based Sustainable Multi-User Computation Offloading for Mobile Edge-Quantum Computing

Learning-Based Sustainable Multi-User Computation Offloading...

引用

IEEE International Conference on Communications (ICC)

作者： Minrui Xu Dusit Niyato Jiawen Kang Zehui Xiong Mingzhe Chen School of Computer Science and Engineering Nanyang Technological University Singapore School of Automation Guangdong University of Technology China Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore Singapore Department of Electrical and Computer Engineering Institute for Data Science and Computing University of Miami Coral Gables FL USA

In this paper, a novel paradigm of mobile edgequantum computing (MEQC) is proposed, which brings quantum computing capacities to mobile edge networks that are closer to mobile users (i.e., edge devices). First, we propose an MEQC system model where mobile users can offload computational tasks to scalable quantum computers via edge servers with cryogenic components and fault-tolerant schemes. Second, we show that it is NP-hard to obtain a centralized solution to the partial offloading problem in MEQC in terms of the optimal latency and energy cost of classical and quantum computing. Third, we propose a multi-agent hybrid discrete-continuous deep reinforcement learning using proximal policy optimization to learn the long-term sustainable offloading strategy without prior knowledge. Finally, experimental results demonstrate that the proposed algorithm can reduce at least 30% of the cost compared with the existing baseline solutions under different system settings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Extending the Design Space of Dynamic Quantum Circuits for Toffoli based Network

Extending the Design Space of Dynamic Quantum Circuits for T...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Abhoy Kole Arighna Deb Kamalika Datta Rolf Drechsler Cyber-Physical Systems DFKI GmbH Bremen Germany School of Electronics Engineering KIIT DU Bhubaneswar India Institute of Computer Science University of Bremen Bremen Germany

Recent advances in fault tolerant quantum systems allow to perform non-unitary operations like mid-circuit measurement, active reset and classically controlled gate operations in addition to the existing unitary gate operations. Real quantum devices that support these non-unitary operations enable us to execute a new class of quantum circuits, known as Dynamic Quantum Circuits (DQC). This helps to enhance the scalability, thereby allowing execution of quantum circuits comprising of many qubits by using at least two qubits. Recently DQC realizations of multi-qubit Quantum Phase Estimation (QPE) and Bernstein-Vazirani (BV) algorithms have been demonstrated in two separate experiments. However the dynamic transformation of complex quantum circuits consisting of Toffoli gate operations have not been explored yet. This motivates us to: (a) explore the dynamic realization of Toffoli gates by extending the design space of DQC for Toffoli networks, and (b) propose a general dynamic transformation algorithm for the first time to the best of our knowledge. More precisely, we introduce two dynamic transformation schemes (dynamic-1 and dynamic-2) for Toffoli gates, that differ with respect to the required number of classically controlled gate operations. For evaluation, we consider the Deutsch-Jozsa (DJ) algorithm composed of one or more Toffoli gates. Experimental results demonstrate that dynamic DJ circuits based on dynamic-2 Toffoli realization scheme provides better computational accuracy over the dynamic-1 scheme. Further, the proposed dynamic transformation scheme is generic and can also be applied to non-Toffoli quantum circuits, e.g. BV algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AI algorithms for Autonomous Robotics Navigation

AI algorithms for Autonomous Robotics Navigation

引用

International Conference on Computational and Characterization Techniques in engineering & sciences (CCTES)

作者： Komala C R J. Raja Sarange Shreepad Marotrao Nalla Neelima R. Sujatha K. Chidambarathanu Department of Information Science and Engineering East Point College of Engineering and Technology Bengaluru Karnataka India Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Mechanical Engineering Ajeenkya D Y Patil School of Engineering Pune Maharashtra India Department of Information Technology R.V.R & J.C. College of Engineering Chowdavaram Andhra Pradesh India Department of Computer Science Subbalakshmi Lakshmipathy College of Science Madurai Tamil Nadu India Department of Computer Science and Business Systems R.M.K. Engineering College Chennai Tamil Nadu India

ISBN: (数字)9798350364699

ISBN: (纸本)9798350364705

Robotic systems depend much on autonomous navigation since it allows them to operate on their own in environments constantly changing and lacking clarity. The most evolved artificial intelligence (AI) techniques applied in self-driving robot navigation are briefly reviewed in this work. These approaches call for classical methodologies, machine learning, and deep learning as well. We examine the advantages and drawbacks of numerous approaches applied in route planning, location finding, map creation, obstacle avoidance. We investigate how neural networks, sensor fusion, and reinforcement learning may be applied to provide increased dependability and flexibility for guiding systems. Case examples illustrating the advantages and drawbacks of applying artificial intelligence (AI) in practical contexts including service robots, drones, and self-driving cars abound. Combining modern AI algorithms with conventional approaches indicates that it is feasible to create self-driving robots more dependable and efficient based on the increased tracking performance.

关键词： Deep learning Navigation Service robots Neural networks Reinforcement learning Sensor fusion Robot sensing systems Planning Artificial intelligence Drones

来源：评论

学校读者我要写书评

暂无评论

An Application of the Partially Observed Markov Process in the Analysis of Transmission Dynamics of COVID-19 via Wastewater

An Application of the Partially Observed Markov Process in t...

引用

2021 IEEE systems and Information engineering Design Symposium, SIEDS 2021

作者： Jiang, Sihang Maggard, Kristen Shakeri, Heman Porter, Michael D. University of Virginia Department of Engineering Systems and Environment CharlottesvilleVA United States University of Virginia Department of Computer Science CharlottesvilleVA United States University of Virginia School of Data Science CharlottesvilleVA United States University of Virginia School of Data Science Department of Engineering Systems and Environment CharlottesvilleVA United States

ISBN: (纸本)9781665412506

As the ongoing outbreak of Coronavirus Disease 2019 (COVID-19) is severely affecting all over the world, analysis of the transmission of COVID-19 is of more and more interest. We focus on the application of compartmental models in the analysis of transmission of COVID-19 based on the detected viral load in wastewater and the reported number of cases. The measurement of COVID-19 RNA concentrations in primary sludge gives us information about the virus prevalence on a population level. Since the transmission of COVID-19 is a partially observed Markov process including different states, we consider a likelihood-based approach to our statistical inference to understand the inner relationship between different states and how COVID-19 actually transmits. Understanding the transmission dynamics of COVID-19 could give suggestions on public policies. © 2021 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Navigation for precise walking of blind people based on pulling illusion devices embedded in white canes 4

Navigation for precise walking of blind people based on pull...

引用

4th IEEE Global Conference on Life sciences and Technologies, LifeTech 2022

作者： Nunokawa, Kiyohiko Tanabe, Takeshi Takizawa, Hotaka Doi, Kouki Ino, Shuichi Tokyo International University School of Human and Social Sciences Kawagoe Japan Industrial Science and Technology Human Informatics and Interaction Research Institute National Institute of Advanced Tsukuba Japan Information and Systems University of Tsukuba Faculty of Engineering Tsukuba Japan National Institute of Special Needs Education Department of Education Information Yokosuka Japan Osaka University Graduate School of Engineering Osaka Japan

ISBN: (纸本)9781665419048

There have been various types of navigation systems for the visually impaired. Many of them were designed to help the visually impaired walk long distances between large landmarks, such as houses and stations. Moreover, short distance navigation is required for the visually impaired. For example, consider a situation where a visually impaired person moves from a table to a counter in a food court. First, he/she can move roughly, but, near the counter, he/she needs to walk carefully not to collide with or pass through the counter. To the best of our knowledge, such a precise navigation has not been focused on in the past. In this study, we proposed a navigation device for precise walking of the visually impaired. The system comprises a white cane and a small vibration actuator embedded in the grip of the white cane. The actuator can generate asymmetric vibrations, enabling the user to feel a pulling illusion. Using this mechanism, the device can notify the user about the directions to walk. In addition, the actuator is so small and light that the user can use the device with one hand, such as the conventional white cane. Besides, we conducted a user study where two sighted participants who wore eye masked and three visually impaired participants walked 10 m to reach a target destination in a corridor environment to evaluate the proposed device's effectiveness. Based on the results, the device can guide the user precisely. © 2022 IEEE.

关键词： Actuators

来源：评论

学校读者我要写书评

暂无评论

OverlapMamba: Novel Shift State Space Model for LiDAR-based Place Recognition

arXiv

引用

arXiv 2024年

作者： Xiang, Qiuchi Cheng, Jintao Luo, Jiehao Wu, Jin Fan, Rui Chen, Xieyuanli Tang, Xiaoyu School of Data Science and Engineering Xingzhi College South China Normal University Shanwei516600 China School of Electronic and Information Engineering South China Normal University Guangdong Foshan528225 China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong College of Intelligence Science and Technology National University of Defense Technology Changsha China College of Electronics & Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems The State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China

Place recognition is the foundation for enabling autonomous systems to achieve independent decision-making and safe operations. It is also crucial in tasks such as loop closure detection and global localization within SLAM. Previous methods utilize mundane point cloud representations as input and deep learning-based LiDAR-based Place Recognition (LPR) approaches employing different point cloud image inputs with convolutional neural networks (CNNs) or transformer architectures. However, the recently proposed Mamba deep learning model, combined with state space models (SSMs), holds great potential for long sequence modeling. Therefore, we developed OverlapMamba, a novel network for place recognition, which represents input range views (RVs) as sequences. In a novel way, we employ a stochastic reconstruction approach to build shift state space models, compressing the visual representation. Evaluated on three different public datasets, our method effectively detects loop closures, showing robustness even when traversing previously visited locations from different directions. Relying on raw range view inputs, it outperforms typical LiDAR and multi-view combination methods in time complexity and speed, indicating strong place recognition capabilities and realtime efficiency. 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

Multi-modal Representation Learning Enables Accurate Protein Function Prediction in Low-Data Setting

arXiv

引用

arXiv 2024年

作者： Ünsal, Serbulent Özdemir, Sinem Kasap, Bünyamin Kalaycı, M. Erşan Turhan, Kemal Doğan, Tunca Acar, Aybar C. Department of Biostatistics and Medical Informatics Faculty of Medicine Graduate School of Health Sciences Karadeniz Technical University Trabzon Turkey Graduate School of Informatics Middle East Technical University Ankara Turkey Health Sciences University Trabzon Kanuni Training and Research Hospital Medical Microbiology Laboratory Trabzon Turkey Biological Data Science Lab Dept. of Computer Engineering Department of Computer Engineering Hacettepe University Ankara Turkey Dept. of Bioinformatics Graduate School of Health Sciences Hacettepe University Ankara Turkey

In this study, we propose HOPER (HOlistic ProtEin Representation), a novel multimodal learning framework designed to enhance protein function prediction (PFP) in low-data settings. The challenge of predicting protein functions is compounded by the limited availability of labeled data. Traditional machine learning models already struggle in such cases, and while deep learning models excel with abundant data, they also face difficulties when data is scarce. HOPER addresses this issue by integrating three distinct modalities—protein sequences, biomedical text, and protein-protein interaction (PPI) networks—to create a comprehensive protein representation. The model utilizes autoencoders to generate holistic embeddings, which are then employed for PFP tasks using transfer learning. HOPER outperforms existing methods on a benchmark dataset across all Gene Ontology categories, i.e., molecular function, biological process, and cellular component. Additionally, we demonstrate its practical utility by identifying new immune-escape proteins in lung adenocarcinoma, offering insights into potential therapeutic targets. Our results highlight the effectiveness of multimodal representation learning for overcoming data limitations in biological research, potentially enabling more accurate and scalable protein function prediction. HOPER source code and datasets are available at https://***/kansil/HOPER © 2024, CC BY-NC-ND.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Recognition of carrier-based aircraft flight deck operations based on dynamic graph

引用

Chinese Journal of Aeronautics 2025年第3期 478-494页

作者： Xingyu GUO Jiaxin LI Hua WANG Junnan LIU Yafei LI Mingliang XU School of Computer Science and Artificial Intelligence Zhengzhou University Engineering Research Center of Intelligent Swarm Systems Ministry of Education National Supercomputing Center in Zhengzhou School of Geo-Science & Technology Zhengzhou University

Accurate recognition of flight deck operations for carrier-based aircraft, based on operation trajectories, is critical for optimizing carrier-based aircraft performance. This recognition involves understanding short-term and long-term spatial collaborative relationships among support agents and positions from long spatial–temporal trajectories. While the existing methods excel at recognizing collaborative behaviors from short trajectories, they often struggle with long spatial–temporal trajectories. To address this challenge, this paper introduces a dynamic graph method to enhance flight deck operation recognition. First, spatial–temporal collaborative relationships are modeled as a dynamic graph. Second, a discretized and compressed method is proposed to assign values to the states of this dynamic graph. To extract features that represent diverse collaborative relationships among agents and account for the duration of these relationships, a biased random walk is then conducted. Subsequently, the Swin Transformer is employed to comprehend spatial–temporal collaborative relationships, and a fully connected layer is applied to deck operation recognition. Finally, to address the scarcity of real datasets, a simulation pipeline is introduced to generate deck operations in virtual flight deck scenarios. Experimental results on the simulation dataset demonstrate the superior performance of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Boundary-Aware Value Function Generation for Safe Stochastic Motion Planning

arXiv

引用

arXiv 2024年

作者： Xu, Junhong Yin, Kai Gregory, Jason M. Hauser, Kris Liu, Lantao Luddy School of Informatics Computing and Engineering Indiana University-Bloomington United States Expedia Group U.S. Army Research Laboratory United States Department of Computer Science University of Illinois at Urbana-Champaign United States

Navigation safety is critical for many autonomous systems such as self-driving vehicles in an urban environment. It requires an explicit consideration of boundary constraints that describe the borders of any infeasible, non-navigable, or unsafe regions. We propose a principled boundary-aware safe stochastic planning framework with promising results. Our method generates a value function that can strictly distinguish the state values between free (safe) and non-navigable (boundary) spaces in the continuous state, naturally leading to a safe boundary-aware policy. At the core of our solution lies a seamless integration of finite elements and kernel-based functions, where the finite elements allow us to characterize safety-critical states’ borders accurately, and the kernel-based function speeds up computation for the non-safety-critical states. The proposed method was evaluated through extensive simulations and demonstrated safe navigation behaviors in mobile navigation tasks. Additionally, we demonstrate that our approach can maneuver safely and efficiently in cluttered real-world environments using a ground vehicle with strong external disturbances, such as navigating on a slippery floor and against external human intervention. © 2024, CC BY.

关键词： Markov processes

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：