检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Liu, Zhengliang Zhong, Tianyang Li, Yiwei Zhang, Yutong Pan, Yi Zhao, Zihao Dong, Peixin Cao, Chao Liu, Yuxiao Shu, Peng Wei, Yaonai Wu, Zihao Ma, Chong Wang, Jiaqi Wang, Sheng Zhou, Mengyue Jiang, Zuowei Li, Chunlin Holmes, Jason Xu, Shaochen Zhang, Lu Dai, Haixing Zhang, Kai Zhao, Lin Chen, Yuanhao Liu, Xu Wang, Peilong Yan, Pingkun Liu, Jun Ge, Bao Sun, Lichao Zhu, Dajiang Li, Xiang Liu, Wei Cai, Xiaoyan Hu, Xintao Jiang, Xi Zhang, Shu Zhang, Xin Zhang, Tuo Zhao, Shijie Li, Quanzheng Zhu, Hongtu Shen, Dinggang Liu, Tianming School of Computing University of Georgia GA United States School of Automation Northwestern Polytechnical University Xi'An710072 China Department of Radiology Massachusetts General Hospital Harvard Medical School MA United States Department of Computer Science and Engineering University of Texas ArlingtonTX United States School of Life Science and Technology University of Electronic Science and Technology of China Chengdu611731 China Glasgow College University of Electronic Science and Technology of China Chengdu611731 China Department of Radiation Oncology Mayo Clinic PhoenixAZ United States Institute of Medical Research Northwestern Polytechnical University Xi'An710072 China School of Physics and Information Technology Shaanxi Normal University Xi'An710119 China School of Computer Science Northwestern Polytechnical University Xi'An710072 China School of Biomedical Engineering ShanghaiTech University Shanghai Clinical Research and Trial Center Shanghai201210 China Shanghai United Imaging Intelligence Co. Ltd. China Department of Biostatistics University of North Carolina at Chapel Hill Chapel HillNC27599 United States Department of Biomedical Engineering Center for Biotechnology Interdisciplinary Studies Rensselaer Polytechnic Institute TroyNY12180 United States Department of Radiology Second Xiangya Hospital Changsha410011 China Shanghai Clinical Research Trial Center China School of Biomedical Engineering Shanghai Jiao Tong University Shanghai200240 China Department of Computer Science and Engineering Lehigh University PA United States Department of Linguistics Department of Computer Science Dartmouth College NH United States Lingang Laboratory Shanghai200031 China

The rise of large language models (LLMs) has marked a pivotal shift in the field of natural language processing (NLP). LLMs have revolutionized a multitude of domains, and they have made a significant impact in the medical field. Large language models are now more abundant than ever, and many of these models exhibit bilingual capabilities, proficient in both English and Chinese. However, a comprehensive evaluation of these models remains to be conducted. This lack of assessment is especially apparent within the context of radiology NLP. This study seeks to bridge this gap by critically evaluating thirty two LLMs in interpreting radiology reports, a crucial component of radiology NLP. Specifically, the ability to derive impressions from radiologic findings is assessed. The outcomes of this evaluation provide key insights into the performance, strengths, and weaknesses of these LLMs, informing their practical applications within the medical domain. © 2023, CC BY.

关键词： Radiology

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Model Incorporating Knowledge Representation Vectors and Its Application in Diabetes Prediction

引用

Disease Markers 2022年第1期2022卷 7593750页

作者： Xu, He Zheng, Qunli Zhu, Jingshu Xie, Zuoling Cheng, Haitao Li, Peng Ji, Yimu School of Computer Science Nanjing University of Posts and Telecommunications Nanjing 210023 China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Jiangsu Province Nanjing 210023 China Institute of High Performance Computing and Big Data Nanjing University of Posts and Telecommunications Nanjing 210023 China Nanjing Center of HPC China Nanjing 210023 China Jiangsu Research Engineering of HPC and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing 210023 China Department of Endocrinology Zhongda Hospital Southeast University Nanjing 210009 China

The deep learning methods for various disease prediction tasks have become very effective and even surpass human experts. However, the lack of interpretability and medical expertise limits its clinical application. This paper combines knowledge representation learning and deep learning methods, and a disease prediction model is constructed. The model initially constructs the relationship graph between the physical indicator and the test value based on the normal range of human physical examination index. And the human physical examination index for testing value by knowledge representation learning model is encoded. Then, the patient physical examination data is represented as a vector and input into a deep learning model built with self-attention mechanism and convolutional neural network to implement disease prediction. The experimental results show that the model which is used in diabetes prediction yields an accuracy of 97.18% and the recall of 87.55%, which outperforms other machine learning methods (e.g., lasso, ridge, support vector machine, random forest, and XGBoost). Compared with the best performing random forest method, the recall is increased by 5.34%, respectively. Therefore, it can be concluded that the application of medical knowledge into deep learning through knowledge representation learning can be used in diabetes prediction for the purpose of early detection and assisting diagnosis. © 2022 He Xu et al.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Observations of cosmic-ray Sun’s shadow with LHAASO-WCDA 38

Observations of cosmic-ray Sun’s shadow with LHAASO-WCDA

引用

38th International Cosmic Ray Conference, ICRC 2023

作者： Cui, Ming-Yang Xia, Jie He, Jia-Yin Shi, Guang-Lu Feng, Li Yuan, Qiang Zhang, Yi Cao, Zhen Aharonian, F. An, Q. Axikegu Bai, Y.X. Bao, Y.W. Bastieri, D. Bi, X.J. Bi, Y.J. Cai, J.T. Cao, Q. Cao, W.Y. Cao, Zhe Chang, J. Chang, J.F. Chen, A.M. Chen, E.S. Chen, Liang Chen, Lin Chen, Long Chen, M.J. Chen, M.L. Chen, Q.H. Chen, S.H. Chen, S.Z. Chen, T.L. Chen, Y. Cheng, N. Cheng, Y.D. Cui, M.Y. Cui, S.W. Cui, X.H. Cui, Y.D. Dai, B.Z. Dai, H.L. Dai, Z.G. Danzengluobu della Volpe, D. Dong, X.Q. Duan, K.K. Fan, J.H. Fan, Y.Z. Fang, J. Fang, K. Feng, C.F. Feng, L. Feng, S.H. Feng, X.T. Feng, Y.L. Gabici, S. Gao, B. Gao, C.D. Gao, L.Q. Gao, Q. Gao, W. Gao, W.K. Ge, M.M. Geng, L.S. Giacinti, G. Gong, G.H. Gou, Q.B. Gu, M.H. Guo, F.L. Guo, X.L. Guo, Y.Q. Guo, Y.Y. Han, Y.A. He, H.H. He, H.N. He, J.Y. He, X.B. He, Y. Heller, M. Hor, Y.K. Hou, B.W. Hou, C. Hou, X. Hu, H.B. Hu, Q. Hu, S.C. Huang, D.H. Huang, T.Q. Huang, W.J. Huang, X.T. Huang, X.Y. Huang, Y. Huang, Z.C. Ji, X.L. Jia, H.Y. Jia, K. Jiang, K. Jiang, X.W. Jiang, Z.J. Jin, M. Kang, M.M. Ke, T. Kuleshov, D. Kurinov, K. Li, B.B. Li, Cheng Li, Cong Li, D. Li, F. Li, H.B. Li, H.C. Li, H.Y. Li, J. Li, Jian Li, Jie Li, K. Li, W.L. Li, W.L. Li, X.R. Li, Xin Li, Y.Z. Li, Zhe Li, Zhuo Liang, E.W. Liang, Y.F. Lin, S.J. Liu, B. Liu, C. Liu, D. Liu, H. Liu, H.D. Liu, J. Liu, J.L. Liu, J.Y. Liu, M.Y. Liu, R.Y. Liu, S.M. Liu, W. Liu, Y. Liu, Y.N. Lu, R. Luo, Q. Lv, H.K. Ma, B.Q. Ma, L.L. Ma, X.H. Mao, J.R. Min, Z. Mitthumsiri, W. Mu, H.J. Nan, Y.C. Neronov, A. Ou, Z.W. Pang, B.Y. Pattarakijwanich, P. Pei, Z.Y. Qi, M.Y. Qi, Y.Q. Qiao, B.Q. Qin, J.J. Ruffolo, D. Sáiz, A. Semikoz, D. Shao, C.Y. Shao, L. Shchegolev, O. Sheng, X.D. Shu, F.W. Song, H.C. Key Laboratory of Dark Matter and Space Astronomy Purple Mountain Observatory Chinese Academy of Sciences Nanjing210023 China School of Astronomy and Space Science University of Science and Technology of China Hefei230026 China Key Laboratory of Particle Astrophyics & Experimental Physics Division & Computing Center Institute of High Energy Physics Chinese Academy of Sciences Beijing100049 China University of Chinese Academy of Sciences Beijing100049 China TIANFU Cosmic Ray Research Center Sichuan Chengdu China Dublin Institute for Advanced Studies 31 Fitzwilliam Place Dublin 2 Ireland Max-Planck-Institut for Nuclear Physics P.O. Box 103980 Heidelberg69029 Germany State Key Laboratory of Particle Detection and Electronics China University of Science and Technology of China Anhui Hefei230026 China School of Physical Science and Technology School of Information Science and Technology Southwest Jiaotong University Sichuan Chengdu610031 China School of Astronomy and Space Science Nanjing University Jiangsu Nanjing210023 China Center for Astrophysics Guangzhou University Guangdong Guangzhou510006 China Hebei Normal University Hebei Shijiazhuang050024 China Key Laboratory of Dark Matter and Space Astronomy Key Laboratory of Radio Astronomy Purple Mountain Observatory Chinese Academy of Sciences Jiangsu Nanjing210023 China Tsung-Dao Lee Institute School of Physics and Astronomy Shanghai Jiao Tong University Shanghai200240 China Key Laboratory for Research in Galaxies and Cosmology Shanghai Astronomical Observatory Chinese Academy of Sciences Shanghai200030 China Key Laboratory of Cosmic Rays [Tibet University Ministry of Education Tibet Lhasa850000 China National Astronomical Observatories Chinese Academy of Sciences Beijing100101 China School of Physics and Astronomy Sun Yat-sen University Zhuhai519000 China School of Physics Guangdong Guangzhou510275 China Sino-French Institute of Nuclear Engineering and Technology Sun Yat-sen Unive

During the propagation of cosmic rays (CRs) in the solar system, they are blocked by the Sun and deflected by the magnetic field, resulting in a shadow on the celestial map. As CRs travel from the vicinity of the Sun to the Earth, they encounter deflection from the coronal magnetic field (CMF), the interplanetary magnetic field (IMF), and finally the geomagnetic field (GMF). The extent of deflection is determined by the magnetic field’s intensity, direction, and energy of the CRs. Variations in the magnetic field cause corresponding changes in the position and size of the Sun’s shadow. By observing the Sun’s shadow of CRs, we can investigate the magnetic fields between the Sun and the Earth, complementing other measurements on these magnetic fields. Furthermore, it serves as a means to validate magnetic field models. The Large high Altitude Air Shower Observatory (LHAASO) is a new generation cosmic-ray and gamma-ray experiment in Daocheng, western China. With a vast Water Cherenkov Detector Array (WCDA) spanning 78,000 m2, LHAASO can successfully observe the significant Sun’s shadow within just a few days. Our study uses the WCDA to measure the Sun’s shadow effect caused by CRs over multiple Carrington rotation periods. Subsequently, we compare these results with simulations based on different magnetic field models. © Copyright owned by the author(s) under the terms of the Creative Commons.

关键词： Cosmic rays

来源：评论

学校读者我要写书评

暂无评论

Dynamic scheduling for stochastic edge-cloud computing environments using A3C learning and residual recurrent neural networks

arXiv

引用

arXiv 2020年

作者： Tuli, Shreshth Ilager, Shashikant Ramamohanarao, Kotagiri Buyya, Rajkumar Laboratory School of Computing and Information Systems University of Melbourne Australia Department of Computer Science and Engineering Indian Institute of Technology Delhi India

The ubiquitous adoption of Internet-of-Things (IoT) based applications has resulted in the emergence of the Fog computing paradigm, which allows seamlessly harnessing both mobile-edge and cloud resources. Efficient scheduling of application tasks in such environments is challenging due to constrained resource capabilities, mobility factors in IoT, resource heterogeneity, network hierarchy, and stochastic behaviors. Existing heuristics and Reinforcement Learning based approaches lack generalizability and quick adaptability, thus failing to tackle this problem optimally. They are also unable to utilize the temporal workload patterns and are suitable only for centralized setups. However, Asynchronous-Advantage-Actor-Critic (A3C) learning is known to quickly adapt to dynamic scenarios with less data and Residual Recurrent Neural Network (R2N2) to quickly update model parameters. Thus, we propose an A3C based real-time scheduler for stochastic Edge-Cloud environments allowing decentralized learning, concurrently across multiple agents. We use the R2N2 architecture to capture a large number of host and task parameters together with temporal patterns to provide efficient scheduling decisions. The proposed model is adaptive and able to tune different hyper-parameters based on the application requirements. We explicate our choice of hyper-parameters through sensitivity analysis. The experiments conducted on real-world data set show a significant improvement in terms of energy consumption, response time, Service-Level-Agreement and running cost by 14.4%, 7.74%, 31.9%, and 4.64%, respectively when compared to the state-of-the-art algorithms. Copyright © 2020, The Authors. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

An effective POS-CNN-based adaptive model for classifying brain tumour from MRI images

引用

AIP Conference Proceedings 2023年第1期2914卷

作者： Sajeev Ram Arumugam L. Thanga Mariappan K. Makanyadevi R. Balakrishna Sankar Ganesh Karuppasamy Department of Computer Science and Engineering Sri Krishna College of Engineering and Technology Coimbatore India Department of Smart Computing School of Information Technology and Engineering Vellore Institute of Technology vellore India Department of Computer science and Engineering M. Kumarasamy College of Engineering Karur India Department of Artificial Intelligence and Data Science Vel Tech High Tech Dr. Rangarajan Dr. Sakunthala Engineering College Chennai India Department of Computer science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India

One of the crucial reasons for death in people is a brain tumour. It will likely develop into malignancy if not appropriately and promptly treated. As a result, early brain tumour diagnosis is a crucial requirement. The Convolutional Neural Network and Particle Swarm Optimization are combined to construct a proposed framework for Brain Tumour Detection from MRI Images. PSO is used to increase segmentation precision and to train the proposed system using CNN. Along with PSO, Scale Invariant Feature Transform (SIFT) is employed as a feature descriptor to improve the system’s classification accuracy. Brain tumour MRI images from the BraTS 2018 dataset were used as input sets for this research. A diagnosis accuracy of 98.76 % was obtained from the results. The proposed technique has better accuracy when the assessment features of the proposed system are evaluated with a few existing approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

high-Rate Four Photon Subtraction from Squeezed Vacuum: Preparing Cat State for Optical Quantum Computation

arXiv

引用

arXiv 2025年

作者： Endo, Mamoru Nomura, Takefumi Sonoyama, Tatsuki Takahashi, Kazuma Takasu, Sachiko Fukuda, Daiji Kashiwazaki, Takahiro Inoue, Asuka Umeki, Takeshi Nehra, Rajveer Marek, Petr Filip, Radim Takase, Kan Asavanant, Warit Furusawa, Akira Department of Applied Physics School of Engineering The University of Tokyo 7-3-1 Hongo Bunkyo Tokyo113-8656 Japan Optical Quantum Computing Research Team RIKEN Center for Quantum Computing 2-1 Hirosawa Saitama Wako351-0198 Japan National Institute of Advanced Industrial Science and Technology 1-1-1 Umezono Ibaraki Tsukuba305-8563 Japan AIST-UTokyo Advanced Operando-Measurement Technology Open Innovation Laboratory 1-1-1 Umezono Ibaraki Tsukuba305-8563 Japan NTT Device Technology Labs NTT Corporation 3-1 Morinosato Wakamiya Kanagawa Atsugi243-0198 Japan Department of Electrical and Computer Engineering University of Massachusetts Amherst 100 Natural Resources Rd AmherstMA01003 United States Department of Physics University of Massachusetts Amherst 100 Natural Resources Rd AmherstMA01003 United States College of Information and Computer Science University of Massachusetts Amherst 100 Natural Resources Rd AmherstMA01003 United States Department of Optics Palacky University 17. listopadu 1192/12 Olomouc77146 Czech Republic

Generating logical qubits, essential for error detection and correction in quantum computation, remains a critical challenge in continuous-variable (CV) optical quantum information processing. The Gottesman-Kitaev-Preskill (GKP) code is a leading candidate for logical qubits, and its generation requires large-amplitude coherent state superpositions—Schrödinger cat states. However, experimentally producing these resource states has been hindered in the optical domain by technical challenges. The photon subtraction method, a standard approach for generating cat states using a squeezed vacuum and a photon number-resolving detector, has proven difficult to scale to multi-photon operations. While the amplitude of the generated cat states increases with the number of subtracted photons, limitations in the generation rate have restricted the maximum photon subtraction to n = 3 for over a decade. In this work, we demonstrate high-rate photon subtraction of up to four photons from a squeezed vacuum with picosecond wavepackets generated by a broadband optical parametric amplifier. Using a Ti-Au superconducting-transition-edge sensor, we achieve high-speed, high-resolution photon number discrimination. The resulting states exhibit Wigner function negativity without loss correction, and their quantum coherence is verified through off-diagonal density matrix elements in CV representation. These results overcome long-standing limitations in multi-photon operations, providing a critical foundation for generating quantum resources essential for fault-tolerant quantum computing and advancing ultrafast optical quantum processors. Copyright © 2025, The Authors. All rights reserved.

关键词： Parametric amplifiers

来源：评论

学校读者我要写书评

暂无评论

Efficient Learning of Continuous-Variable Quantum States

arXiv

引用

arXiv 2023年

作者： Wu, Ya-Dong Zhu, Yan Chiribella, Giulio Liu, Nana John Hopcroft Center for Computer Science Shanghai Jiao Tong University Shanghai200240 China QICI Quantum Information and Computation Initiative Department of Computer Science The University of Hong Kong Pokfulam Road Hong Kong Department of Computer Science Parks Road OxfordOX1 3QD United Kingdom Perimeter Institute for Theoretical Physics WaterlooONN2L 2Y5 Canada Institute of Natural Sciences Shanghai Jiao Tong University Shanghai200240 China Ministry of Education Key Laboratory in Scientific and Engineering Computing Shanghai Jiao Tong University Shanghai200240 China School of Mathematical Sciences Shanghai Jiao Tong University Shanghai200240 China University of Michigan-Shanghai Jiao Tong University Joint Institute Shanghai200240 China

The characterization of continuous-variable quantum states is crucial for applications in quantum communication, sensing, simulation and computing. However, a full characterization of multimode quantum states requires a number of experiments that grows exponentially with the number of modes. Here we propose an alternative approach where the goal is not to reconstruct the full quantum state, but rather to estimate its characteristic function at a given set of points. For multimode states with reflection symmetry, we show that the characteristic function at M points can be estimated using only O(log M) copies of the state, independently of the number of modes. When the characteristic function is known to be positive, as in the case of squeezed vacuum states, the estimation is achieved by an experimentally friendly setup using only beamsplitters and homodyne measurements. © 2023, CC BY-NC-SA.

关键词： Quantum communication

来源：评论

学校读者我要写书评

暂无评论

A survey on few-shot class-incremental learning

arXiv

引用

arXiv 2023年

作者： Tian, Songsong Li, Lusi Li, Weijun Ran, Hang Ning, Xin Tiwari, Prayag Institute of Semiconductors Chinese Academy of Sciences Beijing100083 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China School of Integrated Circuits University of Chinese Academy of Sciences Beijing100083 China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing100083 China Department of Computer Science Old Dominion University NorfolkVA23529 United States School of Information Technology Halmstad University Halmstad30118 Sweden

Large deep learning models are impressive, but they struggle when real-time data is not available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for deep neural networks to learn new tasks from just a few labeled samples without forgetting the previously learned ones. This setup can easily leads to catastrophic forgetting and overfitting problems, severely affecting model performance. Studying FSCIL helps overcome deep learning model limitations on data volume and acquisition time, while improving practicality and adaptability of machine learning models. This paper provides a comprehensive survey on FSCIL. Unlike previous surveys, we aim to synthesize few-shot learning and incremental learning, focusing on introducing FSCIL from two perspectives, while reviewing over 30 theoretical research studies and more than 20 applied research studies. From the theoretical perspective, we provide a novel categorization approach that divides the field into five subcategories, including traditional machine learning methods, meta learning-based methods, feature and feature space-based methods, replay-based methods, and dynamic network structure-based methods. We also evaluate the performance of recent theoretical research on benchmark datasets of FSCIL. From the application perspective, FSCIL has achieved impressive achievements in various fields of computer vision such as image classification, object detection, and image segmentation, as well as in natural language processing and graph. We summarize the important applications. Finally, we point out potential future research directions, including applications, problem setups, and theory development. Overall, this paper offers a comprehensive analysis of the latest advances in FSCIL from a methodological, performance, and application perspective. Copyright © 2023, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Detection of Deepfake videos using long distance attention

arXiv

引用

arXiv 2021年

作者： Lu, Wei Liu, Lingyi Luo, Junwei Zhao, Xianfeng Zhou, Yicong Huang, Jiwu School of Computer Science and Engineering Guangdong Province Key Laboratory of Information Security Technology Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing Sun Yat-sen University Guangzhou510006 China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100195 China School of Cyber Security University of Chinese Academy of Sciences Beijing100195 China Department of Computer and Information Science University of Macau 999078 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518055 China

With the rapid progress of deepfake techniques in recent years, facial video forgery can generate highly deceptive video contents and bring severe security threats. And detection of such forgery videos is much more urgent and challenging. Most existing detection methods treat the problem as a vanilla binary classification problem. In this paper, the problem is treated as a special fine-grained classification problem since the differences between fake and real faces are very subtle. It is observed that most existing face forgery methods left some common artifacts in the spatial domain and time domain, including generative defects in the spatial domain and inter-frame inconsistencies in the time domain. And a spatial-temporal model is proposed which has two components for capturing spatial and temporal forgery traces in global perspective respectively. The two components are designed using a novel long distance attention mechanism. The one component of the spatial domain is used to capture artifacts in a single frame, and the other component of the time domain is used to capture artifacts in consecutive frames. They generate attention maps in the form of patches. The attention method has a broader vision which contributes to better assembling global information and extracting local statistic information. Finally, the attention maps are used to guide the network to focus on pivotal parts of the face, just like other fine-grained classification methods. The experimental results on different public datasets demonstrate that the proposed method achieves the state-of-the-art performance, and the proposed long distance attention method can effectively capture pivotal parts for face forgery. Copyright © 2021, The Authors. All rights reserved.

关键词： Time domain analysis

来源：评论

学校读者我要写书评

暂无评论

Large language model-driven probabilistic trajectory prediction in the Internet of Things using spatio-temporal encoding and normalizing flows

引用

Digital Communications and Networks 2025年

作者： Xiaoliang Wang Liming Xu Lian Zhou Yuzhen Liu Neal Xiong Kuan-Ching Li School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan 411201 China Sanya Institute of Hunan University of Science and Technology Sanya 572024 China Hunan Key Laboratory for Service Computing and Novel Software Technology Xiangtan 411201 China Department of Computer Mathematical and Physical Sciences Sul Ross State University Alpine TX 79830 USA Dept of Computer Science and Information Engineering Providence University Taichung 43301 Taiwan Republic of China

The convergence of the Internet of Things (IoT) and foundation models, particularly Large Language Models (LLMs), heralds a new era of intelligent and adaptive systems. This investigation explores the integration of LLMs and IoT for probabilistic vehicle trajectory prediction, a critical component in autonomous driving. Traditional deterministic models often fail to capture the complexity and uncertainty of real-world driving environments. To address these limitations, we propose an innovative approach that leverages LLM-driven spatio-temporal encoding and normalizing flows. The proposed method extracts latent motion patterns from historical trajectory data using LLMs, providing a nuanced understanding of vehicle dynamics. Advanced spatio-temporal encoders are employed for comprehensive feature extraction, capturing temporal dependencies and spatial relationships. Additionally, scaled dot-product attention is utilized for effective multimodal feature fusion, enhancing the integration of diverse data sources. The normalizing flows framework enhances the model's ability to capture complex, multimodal probability distributions of future trajectories by constructing an invertible transformation network. The network systematically maps simple base distributions to intricate target distributions through reversible transformations, significantly improving prediction accuracy. Evaluation of the nuScenes dataset demonstrates substantial improvements over existing methods. The results underscore the model's capability to generate diverse and realistic trajectory distributions, paving the way for safer and more efficient autonomous driving systems.

关键词： Internet of things Large language models Normalizing flows Spatio-temporal encoding Trajectory prediction

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：