检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wang, Xinlei Feng, Maike Qiu, Jing Gu, Jinjin Zhao, Junhua School of Electrical and Computer Engineering The University of Sydney Australia School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society China

This paper introduces a novel approach that leverages Large Language Models (LLMs) and Generative Agents to enhance time series forecasting by reasoning across both text and time series data. With language as a medium, our method adaptively integrates social events into forecasting models, aligning news content with time series fluctuations to provide richer insights. Specifically, we utilize LLM-based agents to iteratively filter out irrelevant news and employ human-like reasoning to evaluate predictions. This enables the model to analyze complex events, such as unexpected incidents and shifts in social behavior, and continuously refine the selection logic of news and the robustness of the agent's output. By integrating selected news events with time series data, we fine-tune a pre-trained LLM to predict sequences of digits in time series. The results demonstrate significant improvements in forecasting accuracy, suggesting a potential paradigm shift in time series forecasting through the effective utilization of unstructured news data. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Uncertainty propagation in the internet of things

引用

Discover Internet of Things 2024年第1期4卷 1-20页

作者： Pal, Shantanu Khalifa, Sara Miller, Dimity Dedeoglu, Volkan Dorri, Ali Ramachandran, Gowri Moghadam, Peyman Kusy, Brano Jurdak, Raja The School of Information Technology Faculty of Science Engineering and Built Environment Deakin University MelbourneVIC 3125 Australia The School of Information Systems Faculty of Science Queensland University of Technology BrisbaneQLD4000 Australia The School of Electrical Engineering and Robotics Faculty of Engineering Queensland University of Technology BrisbaneQLD4000 Australia The Distributed Sensing Systems Group Data61 CSIRO PullenvaleQLD 4069 Australia The School of Computer Science Faculty of Science Queensland University of Technology BrisbaneQLD 4000 Australia The CSIRO Robotics Data61 CSIRO PullenvaleQLD 4069 Australia

The Internet of Things (IoT) detects context through sensors capturing data from dynamic physical environments, in order to inform automation decisions within cyber physical systems (CPS). Diverse types of uncertainty in the IoT pipeline can propagate within and across nodes, involving complex interactions with security, privacy, and trust that remain largely unexplored. This paper conducts an in-depth analysis of the types of uncertainties in IoT and how they propagate within IoT nodes and networks. We consider adversarial uncertainty in the context of distributed IoT networks to capture perturbations due to malicious actors in the network that can influence IoT security, privacy and trust. We examine the propagation of adversarial uncertainty and well-known uncertainty types, namely aleatoric and epistemic uncertainty, within the five distinct stages of sensing, communication, storage, processing and decision-making in an IoT pipeline, across network layer boundaries, and across nodes within an IoT network. Using this mapping, we analyse the interactions between the uncertainty types and their propagation, and security, privacy, and trust in IoT. Based on this analysis, we discuss guidelines and considerations for mitigating uncertainty in IoT through a smart grid use case study. © The Author(s) 2024.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Meta-learning with orthogonal softmax layer (MLOSL) for small sample hyperspectral image classification

引用

Multimedia Tools and Applications 2025年 1-30页

作者： Amoako, Prince Yaw Owusu Cao, Guo Shi, Hao Arthur, John Kingsley Agyenim, Yaw Oti Boateng School of Computer Science and Engineering Nanjing University of Science and Technology Xiaolingwei Nanjing City210094 China Department of Computer Science Valley View University Accra Oyibi Ghana ETSU Municipal Center East Tennessee State University Johnson CityTN United States

Recent research on Hyperspectral image classification (HSIC) has been much concerned with small sample size due to the challenges of obtaining large labeled data. Coupled with this is the challenge with optimization of the models’ structure and computational complexities. Meta-learning techniques have been proposed to improve classification accuracy on small training data samples. The existing meta-learning techniques still require several pre-collected labeled hyperspectral images (HSI) source datasets of large labeled samples for meta-training, which is undoubtedly a huge task and time-consuming. We propose a meta-learning with orthogonal softmax layer (MLOSL) for small sample HSIC. Orthogonality is introduced to address the structural and computational complexities of deep convolutional neural network (CNN) models for HSIC. An unsupervised meta-learning task construction extracts multiview spectral dimension features of different bands from the same sample, whereas the spatial dimension multiview features are extracted through data augmentation. The orthogonal softmax layer captures a wider variety of patterns in the data by promoting variation among the weight vectors, potentially improving generalization to unobserved samples and minimizing computational time. Label smoothing is added to the classification loss to lessen the impact of incorrectly classified samples and class imbalance. Experimental outcomes on four target datasets compared to existing state-of-the-art models indicate the competitiveness of the proposed model's small sample HSIC performance and its suitability in time-constraint applications. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

India's Stake in Emerging Technology - A Review 18

India's Stake in Emerging Technology - A Review

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Singh, Sugandha China Ramu, S. Lalit, Ruchika Sgt University Department of Computer Science and Engineering Gurugram India Chaitanya Bharathi Institute of Technology Department of Computer Science and Engineering Hyderabad India University School of Automation and Robotics Ggsipu East Campus New Delhi India

ISBN: (纸本)9789380544519

Emerging technologies of today are altering the way we think about the built environment. In the meantime, many technologies have undergone revolutionary changes, and India, an expanding nation, offers opportunities for development in several new areas. The goal of the study is to show how organizations need to adapt their perspective and create new strategies for emerging technologies such as artificial intelligence (AI), machine learning (ML), big data, quantum, and space exploration in light of the swift advancements in technology. This paper presents that although India has come across a lot of advancements in this era of emerging technology, certain challenges have been faced in aspects like adapting, feasibility, and approval which brought many changes across the country, which in turn is impacting the pace to transform the country towards Industry 4.0 and Industry 5.0. Therefore a study is presented to understand the impact of emerging technologies for countries coming up as Industry 4.0 and Industry 5.0. This paper emphasizes on for India's initiatives for emerging technologies to come up as VIKSIT BHARAT @2047. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Artificial Intelligence Big Data Fabrication Hypersonic platforms Industry 4.0 and Industry 5.0 Quantum computing

来源：评论

学校读者我要写书评

暂无评论

Symmetrization of quasi-regular patterns with periodic tilting of regular polygons

引用

Computational Visual Media 2024年第3期10卷 559-576页

作者： Zhengzheng Yin Yao Jin Zhijian Fang Yun Zhang Huaxiong Zhang Jiu Zhou Lili He School of Computer Science and Technology Zhejiang Sci-Tech UniversityHangzhou 310018China Zhejiang Provincial Innovation Center of Advanced Textile Technology Shaoxing 312000China School of Media Engineering Communication University of ZhejiangHangzhou 310018China

computer-generated aesthetic patterns arewidely used as design materials in various fields. Themost common methods use fractals or dynamicalsystems as basic tools to create various patterns. Toenhance aesthetics and controllability, some researchershave introduced symmetric layouts along with thesetools. One popular strategy employs dynamical systemscompatible with symmetries that construct functionswith the desired symmetries. However, these aretypically confined to simple planar symmetries. Theother generates symmetrical patterns under theconstraints of tilings. Although it is slightly moreﬂexible, it is restricted to small ranges of tilingsand lacks textural variations. Thus, we proposed anew approach for generating aesthetic patterns bysymmetrizing quasi-regular patterns using general kuniformtilings. We adopted a unified strategy toconstruct invariant mappings for k-uniform tilings thatcan eliminate texture seams across the tiling ***, we constructed three types of symmetriesassociated with the patterns: dihedral, rotational, andreﬂection symmetries. The proposed method can beeasily implemented using GPU shaders and is highlyefficient and suitable for complicated tiling with regularpolygons. Experiments demonstrated the advantages of our method over state-of-the-art methods in terms ofﬂexibility in controlling the generation of patterns withvarious parameters as well as the diversity of texturesand styles.

关键词： quasi-regular patterns(QRP) k-uniform tilings invariant mappings symmetry aesthetic patterns

来源：评论

学校读者我要写书评

暂无评论

Plant Leaf Diseases Classification Using SVMs, XGBoost, and CNNs Based Texture Features 6

Plant Leaf Diseases Classification Using SVMs, XGBoost, and ...

引用

6th IEEE International Conference on Artificial Intelligence in engineering and Technology, IICAIET 2024

作者： Sami, Abdullah Kamal Al-Dulaimi, Khamael Al-Nahrain University Computer Science Dept. Baghdad Iraq School of Electrical Engineering and Robotics Queensland University of Technology Brisbane Australia

ISBN: (纸本)9798350389692

Plant diseases identification is frequently used by physical examination or laboratory investigation which creates delays that, by the time identification is finished, results in yield loss. Diseases may affect different parts of plant, specifically the leaf. Different Research have made significant contributions to this sector and used computer vision technologies and machine learning effectively. Consequently, having a thorough understanding of the most recent advancements in machine learning technology and its applications for the identification of leaf diseases. In this paper, a technique is proposed by employing texture features with SVM, XGBoost and CNN to identify leaf disease of five types of plants: Alstonia, Gauva, Jamun, Lemon, and Mango. We have used Local Binary Pattern to extract texture features from leaf because the diseases can affect the texture of plant, such as hairs, ridges, and waxy coatings. We have used challenging dataset which taken under different conditions, such as humidity, light, nutrition, water, and temperature which affect the texture, shape, colour and size of leaves. The findings show that the CNN based LBP achieved high accuracy in comparing with others models. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Algorithm-Based Energy-Aware Path Planning with a Quadrotor for Warehouse Inventory Management

HighTech and Innovation Journal

引用

HighTech and Innovation Journal 2023年第4期4卷 829-837页

作者： De Guzman, C.J.P. Chua, A.Y. Chu, T.S. Secco, E.L. Department of Mechanical Engineering De La Salle University 2401 Taft Ave. Malate Manila Philippines Robotics Laboratory School of Mathematics Computer Science & Engineering Liverpool Hope University United Kingdom

Quadrotors have been vital for automating warehouse processes. However, a significant gap in recent studies is that they use a single quadrotor with limited battery life, considering that their objective involves navigation in a large-scale environment such as a warehouse. Using an energy consumption model to enable more efficient navigation can be explored. Conventional data-driven energy models and path planning algorithms are insufficient for describing the various motions that a quadrotor can perform in warehouse operations, such as changes in yaw. This study aims to design a novel exhaustive data-driven energy consumption model and evolutionary algorithm-based path planning algorithm to consider various quadrotor movements involved in warehouse operations. The quadrotor is tasked with performing a set of movements to each be represented as a power equation in terms of their velocity. The obtained equations were subsequently used as the primary optimization objective for the path planning algorithm, which included yaw angle objectives and constraints. A set of experiments was performed with Crazyflie quadrotors to verify the model and the algorithm. The results showcased the accuracy of the energy consumption model, which was kept at a maximum difference of 0.6%. The designed path planning algorithm obtained greater energy efficiency in the generated paths compared to other state-of-the-art evolutionary algorithms with similar objectives and constraints. © Authors retain all.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

FlowNL: Asking the Flow Data in Natural Languages

引用

IEEE Transactions on Visualization and computer Graphics 2023年第1期29卷 1200-1210页

作者： Huang, Jieying Xi, Yang Hu, Junnan Tao, Jun School of Computer Science and Engineering Sun Yat-sen University China National Supercomputer Center Guangzhou China Southern Marine Science and Engineering Guangdong Laboratory Zhuhai China

Flow visualization is essentially a tool to answer domain experts' questions about flow fields using rendered images. Static flow visualization approaches require domain experts to raise their questions to visualization experts, who develop specific techniques to extract and visualize the flow structures of interest. Interactive visualization approaches allow domain experts to ask the system directly through the visual analytic interface, which provides flexibility to support various tasks. However, in practice, the visual analytic interface may require extra learning effort, which often discourages domain experts and limits its usage in real-world scenarios. In this paper, we propose FlowNL, a novel interactive system with a natural language interface. FlowNL allows users to manipulate the flow visualization system using plain English, which greatly reduces the learning effort. We develop a natural language parser to interpret user intention and translate textual input into a declarative language. We design the declarative language as an intermediate layer between the natural language and the programming language specifically for flow visualization. The declarative language provides selection and composition rules to derive relatively complicated flow structures from primitive objects that encode various kinds of information about scalar fields, flow patterns, regions of interest, connectivities, etc. We demonstrate the effectiveness of FlowNL using multiple usage scenarios and an empirical evaluation. © 2022 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

MF-BERT: A Siamese Pre-training Framework for Motion Forecasting

MF-BERT: A Siamese Pre-training Framework for Motion Forecas...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Shi, Jianxin Chen, Jinhao Chen, Xiaolong Ma, Jun Wo, Tianyu School of Computer Science and Engineering Beihang University Beijing China Robotics and Autonomous Systems Thrust The Hong Kong University of Science and Technology Guangzhou China

ISBN: (纸本)9798350368741

Accurately predicting the future motions of traffic agents is essential for autonomous systems. Despite the significant success of existing motion forecasting methods based on supervised learning, they still exhibit two main limitations. First, when annotated data for a scene is limited, these methods often fail to achieve the expected accuracy. Second, they typically rely on complex architectures and extensive prior knowledge to improve performance. To overcome these challenges, we propose MF-BERT, a novel framework that adapts the concept of BERT to motion forecasting, inspired by advancements in the self-supervised pre-training paradigm. During pre-training, we design a siamese sequence modeling task with an asymmetric mask strategy to capture complex behavior patterns of agents. During fine-tuning, the pre-trained representation module initializes the feature encoder of the motion forecasting model, and a multimodal trajectory decoder generates all possible predictions. Experimental results demonstrate the superiority of MF-BERT over state-of-the-art methods. © 2025 IEEE.

关键词： Autonomous Motion Forecasting Self-supervised Learning Time Series Analysis

来源：评论

学校读者我要写书评

暂无评论

Modeling Hybrid Feature-Based Phishing Websites Detection Using Machine Learning Techniques

引用

Annals of Data science 2024年第1期11卷 217-242页

作者： Das Guptta, Sumitra Shahriar, Khandaker Tayef Alqahtani, Hamed Alsalman, Dheyaaldin Sarker, Iqbal H. Department of Computer Science and Engineering Chittagong University of Engineering & ampTechnology Chittagong4349 Bangladesh Unit of Cybersecurity Department of Computer Science Center of Artificial Intelligence King Khalid University Abha Saudi Arabia School of Engineering Computing and Informatics Dar Al-Hekma University Jeddah Saudi Arabia

In this paper, we mainly present a machine learning based approach to detect real-time phishing websites by taking into account URL and hyperlink based hybrid features to achieve high accuracy without relying on any third-party systems. In phishing, the attackers typically try to deceive internet users by masking a webpage as an official genuine webpage to steal sensitive information such as usernames, passwords, social security numbers, credit card information, etc. Anti-phishing solutions like blacklist or whitelist, heuristic, and visual similarity based methods cannot detect zero-hour phishing attacks or brand-new websites. Moreover, earlier approaches are complex and unsuitable for real-time environments due to the dependency on third-party sources, such as a search engine. Hence, detecting recently developed phishing websites in a real-time environment is a great challenge in the domain of cybersecurity. To overcome these problems, this paper proposes a hybrid feature based anti-phishing strategy that extracts features from URL and hyperlink information of client-side only. We also develop a new dataset for the purpose of conducting experiments using popular machine learning classification techniques. Our experimental result shows that the proposed phishing detection approach is more effective having higher detection accuracy of 99.17% with the XG Boost technique than traditional approaches. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022.

关键词： Search engines

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：