检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Jiang, Ye Wang, Taihang Xu, Xiaoman Wang, Yimin Song, Xingyi Maynard, Diana College of Information Science and Technology Qingdao University of Science and Technology China College of Data Science Qingdao University of Science and Technology China Department of Computer Science University of Sheffield United Kingdom

The nascent topic of fake news requires automatic detection methods to quickly learn from limited annotated samples. Therefore, the capacity to rapidly acquire proficiency in a new task with limited guidance, also known as few-shot learning, is critical for detecting fake news in its early stages. Existing approaches either involve fine-tuning pre-trained language models which come with a large number of parameters, or training a complex neural network from scratch with large-scale annotated datasets. This paper presents a multimodal fake news detection model which augments multimodal features using unimodal features. For this purpose, we introduce Cross-Modal Augmentation (CMA), a simple approach for enhancing few-shot multimodal fake news detection by transforming n-shot classification into a more robust (n × z)-shot problem, where z represents the number of supplementary features. The proposed CMA achieves SOTA results over three benchmark datasets, utilizing a surprisingly simple linear probing method to classify multimodal fake news with only a few training samples. Furthermore, our method is significantly more lightweight than prior approaches, particularly in terms of the number of trainable parameters and epoch times. The code is available here: https://***/zgjiangtoby/FND_fewshot. © 2024, CC BY.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Personalized adapter for large meteorology model on devices: towards weather foundation models 24

Personalized adapter for large meteorology model on devices:...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Shengchao Chen Guodong Long Jing Jiang Chengqi Zhang Australian Artificial Intelligence Institute University of Technology Sydney Department of Data Science and AI The Hong Kong Polytechnic University

ISBN: (纸本)9798331314385

This paper demonstrates that pre-trained language models (PLMs) are strong foundation models for on-device meteorological variables modeling. We present LM-WEATHER, a generic approach to taming PLMs, that have learned massive sequential knowledge from the universe of natural language databases, to acquire an immediate capability to obtain highly customized models for heterogeneous meteorological data on devices while keeping high efficiency. Concretely, we introduce a lightweight personalized adapter into PLMs and endows it with weather pattern awareness. During communication between clients and the server, low-rank-based transmission is performed to effectively fuse the global knowledge among devices while maintaining high communication efficiency and ensuring privacy. Experiments on real-wold dataset show that LM-WEATHER outperforms the state-of-the-art results by a large margin across various tasks (e.g., forecasting and imputation at different scales). We provide extensive and in-depth analyses experiments, which verify that LM-WEATHER can (1) indeed leverage sequential knowledge from natural language to accurately handle meteorological sequence, (2) allows each devices obtain highly customized models under significant heterogeneity, and (3) generalize under data-limited and out-of-distribution (OOD) scenarios. Code available on https://***/shengchaochen82/LM-Weather.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Interpretable Ozone Forecasting Approach Based on Deep Learning with Masked Residual Connections

SSRN

引用

SSRN 2025年

作者： Jiménez-Navarro, M.J. Asencio-Cortés, Gualberto Martínez-Álvarez, Francisco Martínez-Ballesteros, María del Mar Department of Computer Languages and Systems University of Seville Av. Reina Mercedes S/N Seville41012 Spain Data Science and Big Data Lab Pablo de Olavide University Ctra. de Utrera 1 Seville41013 Spain

Air pollution is a growing threat, especially in low- and middle-income countries, causing 4.2 million premature deaths annually. Ground-level ozone is a major concern, necessitating accurate and interpretable prediction systems for public health. This study presents a machine learning-based forecasting approach applied in Andalusia, Spain, to improve ozone pollution predictions. Traditional time-series forecasting struggles with handling both linear and non-linear relationships in multi-horizon scenarios. Deep learning models often fail to adapt to these complexities. To address this, the proposed methodology integrates residual connections and feature selection, allowing features with linear relationships to bypass non-linear transformations while creating a hierarchical structure for better adaptability. This approach enhances flexibility, interpretability, and robustness, improving pollution level estimates. Additionally, it provides insights into the impact of individual features, supporting better decision-making in public health. The results demonstrate significant improvements in prediction accuracy and feature relevance assessment. © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Federated Causally Invariant Feature Learning 39

Federated Causally Invariant Feature Learning

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Guo, Xianjie Yu, Kui Cui, Lizhen Yu, Han Li, Xiaoxiao School of Computer Science and Information Engineering Hefei University of Technology China Key Laboratory of Knowledge Engineering with Big Data of Ministry of Education China School of Software Shandong University China College of Computing and Data Science Nanyang Technological University Singapore Department of Electrical and Computer Engineering The University of British Columbia Canada Vector Institute Canada

ISBN: (纸本)157735897X

Federated feature selection (FFS) is a promising field for selecting informative features while preserving data privacy in federated learning (FL) settings. Existing FFS methods focus on capturing the correlations between features and labels. They struggle to achieve satisfactory performance in the face of data distribution heterogeneity among FL clients, and cannot address the out-of-distribution (OOD) problem that arises when a significant portion of clients do not actively participate in FL training. To address these limitations, we propose Federated Causally Invariant Feature Learning (FedCIFL), a novel approach for learning causally invariant features in a privacy-preserving manner. We design a sample reweighting strategy to eliminate spurious correlations introduced by selection bias and iteratively estimate the federated causal effect between each feature and the labels (with the remaining features initially treated as confounders). By iteratively refining the confounding feature set to identify the true confounders, FedCIFL mitigates the impact of limited local data on the accuracy of federated causal effect estimation. Theoretical analysis proves the correctness of FedCIFL under reasonable assumptions. Extensive experiments on synthetic and real-world datasets demonstrate the superiority of FedCIFL against eight state-of-the-art baselines, beating the best-performing approach by 3.19%, 9.07% and 2.65% in terms of average test Accuracy, RMSE and F1 score, respectively. It is a first-of-its-kind FFS approach capable of handling Non-IID and OOD data simultaneously. The source code is available at https://***/Xianjie-Guo/FedCIFL. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Perspective Chapter: MOOCs in India: Evolution, Innovation, Impact, and Roadmap

arXiv

引用

arXiv 2025年

作者： Das, Partha Pratim Department of Computer Science Center for Data Science and Analytics Ashoka University Sonepat India Department of Computer Science and Engineering Indian Institute of Technology Kharagpur Kharagpur India

With the largest population of the world and one of the highest enrolments in higher education, India needs efficient and effective means to educate its learners. India started focusing on open and digital education in 1980's and its efforts were escalated in 2009 through the NMEICT program of the Government of India. A study by the Government and FICCI in 2014 noted that India cannot meet its educational needs just by capacity building in brick and mortar institutions. It was decided that ongoing MOOCs projects under the umbrella of NMEICT will be further strengthened over its second (2017-21) and third (2021-26) phases. NMEICT now steers NPTEL/SWAYAM (India's MOOCs) and several digital learning projects including Virtual Labs, e-Yantra, Spoken Tutorial, FOSSEE, and National Digital Library on India-the largest digital education library in the world. Further, India embraced its new National Education Policy in 2020 to strongly foster online education. In this chapter, we take a deep look into the evolution of MOOCs in India, its innovations, its current status and impact, and the roadmap for the next decade to address its challenges and grow. AI-powered MOOCs is an emerging opportunity for India to lead MOOCs worldwide. © 2025, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring the Impact of Herbal Remedies on Autism Spectrum Disorder Using AGLSTM Analysis

Exploring the Impact of Herbal Remedies on Autism Spectrum D...

引用

Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： Bagiyalakshmi N T. Veeramakali Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulathur

Autism is a personality disorder that can cause significant emotional, intellectual, and behavioral deficits. Autism is recognized as an illness on the spectrum because, while certain kids might have mild symptoms, others may have extensive life-challenging abnormalities. However, autistic people have unique characteristics and health goals and may react differently to conventional or herbal therapy than others. Herbal medications might be a possible approach to helping autistic people's bodies and brains. However, further research is needed to determine whether herbal therapy is useful for autistic individuals. To gain insight into how people think regarding herbal medication for autism, data must be processed promptly as it is generated, which may be accomplished using sentiment assessment, which analyzes polarization in writings. This paper proposes the AGLSTM Model, a hybrid model that solves the sentiment evaluation issue by combining LSTM with agglomerative clustering. The suggested system signifies text data into numerical vectors that illustrate text features such as the frequency of words and embeddings of phrases using the TF-IDF technique and the word2vec model. Every word becomes assigned to a cluster using a method known as clustering based on how similar it is to the cluster nucleus or other texts in the region. The outcome of the experiment is a set of clusters composed of sentences with comparable emotional content. The LSTM framework can detect long-term correlations between word patterns and classify feedback as positive or negative.

关键词：

来源：评论

学校读者我要写书评

暂无评论

One-shot Human Motion Transfer via Occlusion-Robust Flow Prediction and Neural Texturing

引用

IEEE Transactions on Multimedia 2025年

作者： Ji, Yuzhu Zheng, Chuanxia Cham, Tat-Jen Guangdong University of Technology School of Computer Science and Technology Guangzhou510006 China University of Oxford Department of Engineering Science Oxford United Kingdom Nanyang Technological University College of Computing and Data Science Singapore Singapore

Human motion transfer aims at animating a static source image with a driving video. While recent advances in one-shot human motion transfer have led to significant improvement in results, it remains challenging for methods with 2D body landmarks, skeleton and semantic mask to accurately capture correspondences between source and driving poses due to the large variation in motion and articulation complexity. In addition, the accuracy and precision of DensePose degrade the image quality for neural-rendering-based methods. To address the limitations and by both considering the importance of appearance and geometry for motion transfer, in this work, we proposed a unified framework that combines multi-scale feature warping and neural texture mapping to recover better 2D appearance and 2.5D geometry, partly by exploiting the information from DensePose, yet adapting to its inherent limited accuracy. Our model takes advantage of multiple modalities by jointly training and fusing them, which allows it to robust neural texture features that cope with geometric errors as well as multi-scale dense motion flow that better preserves appearance. Experimental results with full and half-view body video datasets demonstrate that our model can generalize well and achieve competitive results, and that it is particularly effective in handling challenging cases such as those with substantial self-occlusions. © 1999-2012 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Systems for Autonomous IoT Network Management Using Distributed Reinforcement Learning 3

Multi-Agent Systems for Autonomous IoT Network Management Us...

引用

3rd International Conference on Intelligent Systems, Advanced Computing, and Communication, ISACC 2025

作者： Neelamegam, G. Venkatesan, Rajaram Ramya, S.R. Ramya, R.S. Akshya, J. Sundarrajan, M. Choudhry, Mani Deepak VSB College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Coimbatore India Builders Engineering College Department of Artificial Intelligence and Data Science Tamil Nadu Tirupur India Dr NGP Institute of Technology Department of Computer Science and Engineering Tamil Nadu Coimbatore India Sri Ramakrishna Engineering College Department of Computer Science and Engineering Tamil Nadu Coimbatore India SRM Institute of Science and Technology Department of Computational Intelligence Tamil Nadu Chennai India SRM Institute of Science and Technology Department of Networking and Communications Tamil Nadu Chennai India SRM Institute of Science and Technology Department of Computing Technologies Tamil Nadu Chennai India

ISBN: (纸本)9798331523893

The ever-growing complexity of IoT networks ignited by their wide scale adoption in applications such as smart cities, the industrial automation, and health care, compelled to develop sophisticated yet resource efficient and scalable network management solution. Centralized systems are traditional in architecture, which leads to higher latency and bottlenecks, while decentralized systems can distribute workloads however the lack of adaptability to real time, along with the difficulty of extracting maximum resource usage, are limitations. In recent years, reinforcement learning (RL) based approaches have taken shape as a promising alternative to facilitate the automated learning and optimisation of task management. However, there are two challenges for existing RL based methods: slow convergence, inefficient priority assignment of tasks, and poor coordination amongst agents in the case of dynamic, large scale IoT environment. To solve these challenges, in this research we propose a distributed reinforcement learning based multi agent framework for managing IoT network. The framework also integrates a task prioritization mechanism to dynamically choose an optimal task allocation solution. Further validation was performed in a simulated IoT environment where real world inspired datasets were used. The proposed framework demonstrated 30% more task throughput than centralized, 25% less latency than decentralized, and 40% more energy efficiency than current RL based systems. The system was further validated using advanced visualizations such as anomaly detection maps and resource allocation efficiency graphs, demonstrating its capacity to manage dynamic load of tasks and resource allocation. The proposed framework addresses the critical limitations of current methods, through scalable, adaptive, and energy efficient framework for managing IoT network, and accordingly helps advancing the intelligent and autonomous IoT systems. © 2025 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Voice-Recognition Wheelchair System for Disabled Persons

An Intelligent Voice-Recognition Wheelchair System for Disab...

引用

2023 International Conference on Sustainable Computing and Smart Systems, ICSCSS 2023

作者： Kalpana, A.V. Venkataramanan, V. Charulatha, G. Geetha, G. Srm Institute of Science and Technology Department of Data Science and Business Systems Tamil Nadu Chennai India D.J Sanghvi College of Engineering Department of Electronics and Communication Engineering Maharashtra Mumbai India Peri Institute of Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India B v Raju Institute of Technology Department of Computer Science Engineering Telangana Hyderabad India

ISBN: (纸本)9798350333602

This study illustrates the creation of an intelligent voice-recognition wheelchair for disabled persons who cannot manually man-oeuvre their wheelchairs. Using voice recognition, the patient operates the wheelchair, and a GPS device included in the wheelchair can track the patient's position and communicate the data to a Smartphone. To carry out the people's orders, the voice module V3 records and can recognize the patient's voice. This module converts the voice commands into letters, subsequently transmitted to the Wi-Fi module to operate the wheelchair. The Wi-Fi module sends commands to the motor drive for the wheels. In addition, three levels of motor speed adjustment are available: low, medium, and high. This device also utilizes an Infrared sensor to automatically identify obstacles, allowing the patient's family members to know exactly where they are. Disabled People can be used this device, which simultaneously provides a voice-controlled wheelchair, obstacle detection, motor speed control, and patient GPS tracking via mobile phone;it will be a successful solution for disabled people across the world. © 2023 IEEE.

关键词： Wheelchairs

来源：评论

学校读者我要写书评

暂无评论

Dynamical Fluctuations of Random Walks in Higher-Order Networks

引用

Physical Review Letters 2024年第10期133卷 107401页

作者： Leonardo Di Gaetano Giorgio Carugno Federico Battiston Francesco Coghi Department of Network and Data Science Department of Mathematics KTH Royal Institute of Technology and Stockholm University Hannes Alfvéns väg 12 SEa-106 91 Stockholm Sweden

Although higher-order interactions are known to affect the typical state of dynamical processes giving rise to new collective behavior, how they drive the emergence of rare events and fluctuations is still an open problem. We investigate how fluctuations of a dynamical quantity of a random walk exploring a higher-order network arise over time. In the quenched case, where the hypergraph structure is fixed, through large deviation theory we show that the appearance of rare events is hampered in nodes with many higher-order interactions, and promoted elsewhere. Dynamical fluctuations are further boosted in an annealed scenario, where both the diffusion process and higher-order interactions evolve in time. Here, extreme fluctuations generated by optimal higher-order configurations can be predicted in the limit of a saddle-point approximation. Our study lays the groundwork for a wide and general theory of fluctuations and rare events in higher-order networks.

关键词： Network diffusion Random graphs Diffusion & random walks Large deviation & rare event statistics

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：