检索结果-内蒙古大学图书馆

ST-Booster: An Iterative SpatioTemporal Perception Booster for Vision-and-Language Navigation in Continuous Environments

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yue, Lu Zhou, Dongliang Xie, Liang Yin, Erwei Zhang, Feitian Department of Advanced Manufacturing and Robotics the State Key Laboratory of Turbulence and Complex Systems College of Engineering Peking University Beijing100871 China Defense Innovation Institute Academy of Military Sciences Beijing100071 China Tianjin Artificial Intelligence Innovation Center Tianjin300450 China Department of Computer Science Harbin Institute of Technology Shenzhen Xili University Town Shenzhen518055 China

Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to navigate unknown, continuous spaces based on natural language instructions. Compared to discrete settings, VLN-CE poses two core perception challenges. First, the absence of predefined observation points leads to heterogeneous visual memories and weakened global spatial correlations. Second, cumulative reconstruction errors in three-dimensional scenes introduce structural noise, impairing local feature perception. To address these challenges, this paper proposes ST-Booster, an iterative spatiotemporal booster that enhances navigation performance through multi-granularity perception and instruction-aware reasoning. ST-Booster consists of three key modules — Hierarchical SpatioTemporal Encoding (HSTE), Multi-Granularity Aligned Fusion (MGAF), and Value-Guided Waypoint Generation (VGWG). HSTE encodes long-term global memory using topological graphs and captures short-term local details via grid maps. MGAF aligns these dual-map representations with instructions through geometry-aware knowledge fusion. The resulting representations are iteratively refined through pretraining tasks. During reasoning, VGWG generates Guided Attention Heatmaps (GAHs) to explicitly model environment-instruction relevance and optimize waypoint selection. Extensive comparative experiments and performance analyses are conducted, demonstrating that ST-Booster outperforms existing state-of-the-art methods, particularly in complex, disturbance-prone environments. Copyright © 2025, The Authors. All rights reserved.

关键词： Topology

xLSTM-UNet can be an Effective 2D & 3D Medical Image Segmentation Backbone with Vision-LSTM (ViL) better than its Mamba Counterpart

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Tianrun Ding, Chaotao Zhu, Lanyun Xu, Tao Ji, Deyi Wang, Yan Zang, Ying Li, Zejian College of Computer Science and Technology Zhejiang University China Tech. Co. LTD China School of Information Engineering Huzhou University China Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore School of Software Technology Zhejiang University China School of Information Science and Technology University of Science and Technology of China China School of Instrumentation and Optoelectronic Engineering State Key Laboratory of Software Development Environment Beihang University China

Convolutional Neural Networks (CNNs) and Vision Transformers (ViT) have been pivotal in biomedical image segmentation. Yet, their ability to manage long-range dependencies remains constrained by inherent locality and computational overhead. To overcome these challenges, in this technical report, we first propose xLSTM-UNet, a UNet structured deep learning neural network that leverages Vision-LSTM (xLSTM) as its backbone for medical image segmentation. xLSTM has recently been proposed as the successor of Long Short-Term Memory (LSTM) networks and has demonstrated superior performance compared to Transformers and State Space Models (SSMs) like Mamba in Neural Language Processing (NLP) and image classification (as demonstrated in Vision-LSTM, or ViL implementation). Here, xLSTM-UNet we designed to extend the success in the biomedical image segmentation domain. By integrating the local feature extraction strengths of convolutional layers with the long-range dependency-capturing abilities of xLSTM, xLSTM-UNet offers a robust solution for comprehensive image analysis. We validate the efficacy of xLSTM-UNet through experiments. Our findings demonstrate that xLSTM-UNet consistently surpasses the performance of leading CNN-based, Transformer-based, and Mamba-based segmentation networks in multiple datasets in biomedical segmentation including organs in abdomen MRI, instruments in endoscopic images, and cells in microscopic images. With comprehensive experiments performed, this technical report highlights the potential of xLSTM-based architectures in advancing biomedical image analysis in both 2D and 3D. The code, models, and datasets are publicly available at http://***/xLSTM-Unet/. © 2024, CC BY-NC-ND.

关键词： Long short-term memory

Exploring structure diversity in atomic resolution microscopy with graph neural networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Luo, Zheng Feng, Ming Gao, Zijian Yu, Jinyang Hu, Liang Wang, Tao Xue, Shenao Zhou, Shen Ouyang, Fangping Feng, Dawei Xu, Kele Wang, Shanshan Department of Materials Hunan Key Laboratory of Mechanism and Technology of Quantum Information College of Aerospace Science and Engineering National University of Defense Technology Changsha410000 China School of Computer State Key Laboratory of Complex & Critical Software Environment National University of Defense Technology Changsha410000 China College of Electronic and Information Engineering Tongji University Shanghai201804 China School of Material Science and Engineering Peking University Beijing100871 China School of Physics Central South University Changsha410083 China College of Science National University of Defense Technology Changsha410000 China School of Advanced Materials Peking University Shenzhen Graduate School Guangdong Shenzhen518055 China

The emergence of deep learning (DL) has provided great opportunities for the high-throughput analysis of atomic-resolution micrographs. However, the DL models trained by image patches in fixed size generally lack efficiency and flexibility when processing micrographs containing diversified atomic configurations. Herein, inspired by the similarity between the atomic structures and graphs, we describe a few-shot learning framework based on an equivariant graph neural network (EGNN) to analyze a library of atomic structures (e.g., vacancies, phases, grain boundaries, doping, etc.), showing significantly promoted robustness and three orders of magnitude reduced computing parameters compared to the image-driven DL models, which is especially evident for those aggregated vacancy lines with flexible lattice distortion. Besides, the intuitiveness of graphs enables quantitative and straightforward extraction of the atomic-scale structural features in batches, thus statistically unveiling the self-assembly dynamics of vacancy lines under electron beam irradiation. A versatile model toolkit is established by integrating EGNN sub-models for single structure recognition to process images involving varied configurations in the form of a task chain, leading to the discovery of novel doping configurations with superior electrocatalytic properties for hydrogen evolution reactions. This work provides a powerful tool to explore structure diversity in a fast, accurate, and intelligent manner. Copyright © 2024, The Authors. All rights reserved.

关键词： Grain boundaries

A Novel YJQR-LSTM Model for Nonparametric Probabilistic Sustainable Agriculture Wind Power Forecasting Based on Intelligent IoT

学校读者我要写书评

暂无评论

IEEE Internet of Things Journal 2024年

作者： Wang, Jie Jiang, Junhui Chen, Xinlong Cai, Defu Wu, Yue Lu, Renzhi School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Harbin Engineering University College of Computer Science and Technology Harbin150001 China State Grid Hubei Electric Power Research Institute Hubei Wuhan430079 China School of Technology State Key Laboratory of Efficient Production of Forest Resources Key Laboratory of National Forestry and Grassland Administration on Forestry Equipment and Automation Beijing Forestry University Beijing100083 China Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Industrial Internet of Things and Networked Control Ministry of Education Chongqing400065 China State Key Laboratory of Mechanical Transmission for Advanced Equipment Chongqing University Chongqing400044 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China

Energy costs associated with the consumption of non-renewable energy sources have become an important issue in improving the international competitiveness of agriculture. Wind power, as a renewable energy source, can replace non-renewable energy sources to reduce energy costs and improve the sustainability of agricultural. However, the inherent intermittency, randomness, and volatility within weather conditions and wind speed presents a substantial challenge in accurately predicting wind power generation. This work proposes a novel YJQR-LSTM algorithm that leverages Yeo-Johnson quantile regression (YJQR) with a long short-term memory (LSTM) network for nonparametric probabilistic forecasting of wind power generation via the Intelligent Internet of Things. First, an improved YJQR model based on the YJ transformation is designed to obtain a more precise characterization of wind uncertainty, providing a more flexible probability density function for wind power generation. Then, utilizing the unique structure of the LSTM network to learn the parameters of the YJQR model, temporal features can be extracted from time series data. To mitigate the impact of outliers in the raw data on accuracy and improve computational efficiency, a novel logarithmic likelihood function is developed as the loss function utilized in the training phase. The effectiveness of the proposed algorithm is validated using a real-world dataset from five wind farms from the Global Energy Forecasting Competition. Numerical results demonstrate that the algorithm provides more accurate wind power prediction results in complex wind power data environments, which is important for making full use of wind energy and thus reducing the consumption of non-renewable energy in agriculture. © 2024 IEEE.

关键词： Wind forecasting

Harmonic-Coupled Riccati Equation and its Applications in Distributed Filtering

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Qian, Jiachen Duan, Peihu Duan, Zhisheng Shi, Ling State Key Laboratory for Turbulence and Complex Systems Department of Mechanics and Engineering Science College of Engineering Peking University Beijing100871 China School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Department of Electronic and Computer Engineering the Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong

The coupled Riccati equations (CREs) are a set of multiple Riccati-like equations whose solutions are coupled with each other through matrix means. They are a fundamental mathematical tool to depict the inherent dynamics of many complex systems, including Markovian systems or multi-agent systems. This paper investigates a new kind of CREs called harmonic-coupled Riccati equations (HCREs), whose solutions are coupled using harmonic means. We first introduce the specific form of HCREs and then analyze the existence and uniqueness of its solutions under the conditions of collective observability and primitiveness of coupling matrices. Additionally, we ensure the uniqueness of HCREs solutions with several mild conditions. Based on this newly established theory, we greatly simplify the steady-state estimation error covariance of consensus-on-information-based distributed filtering (CIDF) into the solutions to a discrete-time Lyapunov equation (DLE). This leads to a significant conservativeness reduction of traditional performance evaluation techniques for CIDF. The obtained results are remarkable since they not only enrich the theory of CREs, but also provide a novel insight into the synthesis and analysis of CIDF algorithms. We finally validate our theoretical findings through several numerical experiments. Copyright © 2022, The Authors. All rights reserved.

关键词： Multi agent systems

Comparison of two newly suggested power, refrigeration, and hydrogen production, for moving towards sustainability schemes using improved solar-powered evolutionary algorithm optimization

学校读者我要写书评

暂无评论

Chemosphere 2023年第1期336卷 139160页

作者： Hai, Tao Abd El-Salam, Nasser M. Kh, Teeba Ismail Chaturvedi, Rishabh El-Shafai, Walid Farhang, Babak School of Computer and Information Qiannan Normal University for Nationalities Guizhou Duyun558000 China Key Laboratory of Complex Systems and Intelligent Optimization of Guizhou Province Guizhou Duyun558000 China Universiti Teknologi MARA Selangor Shah Alam40450 Malaysia Natural Science Department Community College King Saud University Riyadh12642 Saudi Arabia Department of Computer Engineering College of Engineering and Computer Science Lebanese French University Kurdistan Region Iraq Department of Mechanical Engineering Institute of Engineering & Technology GLA University UP Mathura281001 India Department Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Energy Technology Aalborg University Denmark

In the third millennium, developing countries will confront significant environmental problems such as ozone depletion, global warming, the shortage of fossil resources, and greenhouse gas emissions. This research looked at a multigenerational system that can generate clean hydrogen, fresh water, electricity, heat, and cooling. The system's components include Rankine and Brayton cycles, an Organic Rankine Cycle (ORC), flash desalination, an Alkaline electrolyzer, and a solar heliostat. The proposed process has been compared for two different start-up modes with a combustion chamber and solar heliostat to compare renewable and fossil fuel sources. This research evaluated various characteristics, including turbine pressure, system efficiency, solar radiation, and isentropic efficiency. The energy and exergy efficiency of the proposed system were obtained at around 78.93% and 47.56%, respectively. Exergy study revealed that heat exchangers and alkaline electrolyzers had the greatest exergy destruction rates, at 78.93% and 47.56%, respectively. The suggested system produces 0.04663 kg/s of hydrogen. Results indicate that at the best operational conditions, the exergetic efficiency, power, and hydrogen generation of 56%, 6000 kW, and 1.28 kg/s is reached, respectively. Also, With a 15% improvement in the Brayton cycle's isentropic efficacy, the quantity of hydrogen produced increases from 0.040 kg/s to 0.0520 kg/s. © 2023 Elsevier Ltd

关键词： Solar energy

Observability Analysis and Reduced-Order Observer Design for a Super-Coiled Polymer-Driven Robotic Eye

学校读者我要写书评

暂无评论

Observability Analysis and Reduced-Order Observer Design for...

IEEE Conference on Decision and Control

作者： Sunil Kumar Rajendran Qi Wei Ningshi Yao Feitian Zhang Department of Electrical and Computer Engineering George Mason University Fairfax VA USA Department of Bioengineering George Mason University Fairfax VA USA Department of Advanced Manufacturing and Robotics and the State Key Laboratory of Turbulence and Complex Systems College of Engineering Peking University Beijing China

ISBN: (数字)9781665467612

ISBN: (纸本)9781665467629

With the aid of a robotic eye platform, several ocular motor disorders such as strabismus can be studied by ophthalmologists and biomedical researchers to better under-stand the biomechanisms of the human eye. Our previous work modeled a 2-DOF robotic eye driven by Super-Coiled Polymer (SCP) artificial muscles and presented a Deep Deterministic Policy Gradient (DDPG) learning-based controller. The control policy requires access to the full system states that include the orientation of the robotic eye and temperature changes of the SCPs. While the angular orientations of the robotic eye can be determined using embedded sensors or image-processing of the visual feed, it is quite laborious and expensive to measure the temperatures of the slender SCP muscles without affecting robot dynamics. To address this problem, this paper designs a linear reduced-order state observer based on the linearization of the nonlinear dynamics of the robotic eye. The linearized model is analytically shown to be fully observable along any trajectory within the operation range. To quantify the local observability of the dynamical system, local unobservability indices and local estimation condition numbers are determined along trajectories of the system states. The performance of the designed observer is tested through simulation in both open-loop and closed-loop foveation control of the robotic eye.

关键词： Temperature sensors Temperature measurement Visualization Observers Robot sensing systems Trajectory Nonlinear dynamical systems

Gathering GitHub OSS Requirements from Q&A Community: an Empirical Study

学校读者我要写书评

暂无评论

Gathering GitHub OSS Requirements from Q&A Community: an Emp...

IEEE International Conference on engineering of complex computer systems

作者： Hao Huang Yao Lu Xinjun Mao Key Laboratory of Software Engineering for Complex Systems College of Computer National University of Defense Technology Changsha China

ISBN: (数字)9781728185583

ISBN: (纸本)9781728185590

Cross-community collaboration can exploit the expertise and knowledges of crowds in different communities. Recently increasing users in open source software (OSS) community like GitHub attempt to gather software requirements from question and answer (Q&A) communities such as Stack Overflow (SO). In order to investigate this emerging cross-community collaboration phenomenon, the paper presents an exploratory study on cross-community requirements gathering of OSS projects in GitHub. We manually sample 3266 practice cases and quantitatively analyze the popularity of the phenomenon, the characteristics of the gathered requirements, and cross-community collaboration behaviors of users. Some important findings are obtained: more than half of the requirements gathered from SO are enhancements and the majority of the gathered requirements are non-functional requirements. In addition, OSS developers can directly obtain related solutions and contributions of the gathered requirements from SO in the gathering process.

关键词： Collaboration Manuals Tools software Time factors Open source software software development management

AgInS_(2)/ZnS quantum dots for noninvasive cervical cancer screening with intracellular pH sensing using fluorescence lifetime imaging microscopy

学校读者我要写书评

暂无评论

Nano Research 2022年第6期15卷 5193-5204页

作者： Wenhua Su Dan Yang Yulan Wang Yawei Kong Wanlu Zhang Jing Wang Yiyan Fei Ruiqian Guo Jiong Ma Lan Mi Department of Optical Science and Engineering Shanghai Engineering Research Center of Ultra-precision Optical ManufacturingKey Laboratory of Micro and Nano Photonic Structures(Ministry of Education)School of Information Science and TechnologyFudan UniversityShanghai 200433China Institute for Electric Light Sources School of Information Science and TechnologyFudan UniversityShanghai 200433China Department of Gynecology and Obstetrics The Central Hospital of WuhanTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430014China Institute of Photonic Chips University of Shanghai for Science and TechnologyShanghai 200093China Centre for Artificial-Intelligence NanophotonicsSchool of Optical-Electrical and Computer EngineeringUniversity of Shanghai for Science and TechnologyShanghai 200093China Institute of Biomedical Engineering and Technology Academy for Engineer and TechnologyFudan University220 Handan RoadShanghai 200433China Shanghai Engineering Research Center of Industrial Microorganisms the Multiscale Research Institute of Complex Systems(MRICS)School of Life SciencesFudan University220 Handan RoadShanghai 200433China

Intracellular pH plays a critical role in biological functions,and abnormal pH values are related to various ***,we report on an intracellular pH sensor AgInS_(2)(AIS)/ZnS quantum dots(QDs)that show long fluorescence lifetimes of hundreds of nanoseconds and low *** lifetime imaging microscopy(FLIM)combined with AIS/ZnS QDs is used for the imaging of live cells in different pH buffers and different cell *** FLIM images of AIS/ZnS QDs in live cells demonstrate different intracellular pH values in different regions,such as in lysosomes or *** method can also distinguish cancer cells from normal cells,and the fluorescence lifetime difference of the AIS/ZnS QDs between the two types of cells is 100±7 *** importantly,the exfoliated cervical cells from 20 patients are investigated using FLIM combined with AIS/ZnS *** lifetime difference value between the normal and cervical cancer(CC)groups is 115±9 ns,and the difference between the normal and the precancerous lesion group is 64±9 *** the first time,the noninvasive method has been used for cervical cancer screening,and it has shown great improvement in sensitivity compared with a clinical conventional cytology examination.

关键词： AIS/ZnS quantum dots fluorescence lifetime imaging microscopy intracellular pH sensing cervical cancer screening noninvasive