检索结果-内蒙古大学图书馆

Big data in Social Media: Analyzing Trends, Patterns and Challenges 2

学校读者我要写书评

暂无评论

Big Data in Social Media: Analyzing Trends, Patterns and Cha...

2nd International Conference on machine learning and Autonomous Systems, ICMLAS 2025

作者： Jikar, Nayan Tale, Yash Tale, Abhay Barhate, Aditya Verma, Prateek Jikar, Aman Datta Meghe Institute of Higher Education and Research Sawangi Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Maharashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Sawangi Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Maharashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Computer Science and Engineering Maharashtra Wardha442001 India

ISBN: (纸本)9798331505745

The huge volumes of data produced in social media provide both new possibilities and challenges to analytics. The present paper emphasizes Big data analytics and machine learning (ML) methods to uncover trends, patterns, and user behavior from social media-related data. Such vital concepts, like the 'Four Vs' of Big data: Volume, Velocity, Variety, and Veracity, and innovative tools for datacollection, storage, and preprocessing are covered here as well. Sentiment analysis, trend forecasting, and user behaviormodeling are some of the examples of what is possible using ML and Artificial Intelligence (AI) for deriving actionable insights. Marketing campaigns, crisis communications, and political campaigns are some of the scenarios that are covered to bring out real world applications of such technologies, along with their transformative effects. Lastly, data privacy, quality, and scalability issues are noted, along with ethical concerns and biases. Directions for the future point to developments in real-time data analysis, anonymization, and the changing role of AI in social media platforms. This research emphasizes the significance of Big data and machine learning in driving innovation and decision-making in the digital era. © 2025 IEEE.

关键词： Tweets

A Theoretical Analysis of Self-Supervised learning for Vision Transformers

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Huang, Yu Wen, Zixin Chi, Yuejie Liang, Yingbin UPenn United States CMU United States OSU United States Department of Statistics and Data Science Wharton School University of Pennsylvania United States Machine Learning Department Carnegie Mellon University United States Department of Electrical and Computer Engineering Carnegie Mellon University United States Department of Electrical and Computer Engineering The Ohio State University United States

Self-supervised learning (SSL) has become a foundational approach in computer vision, which is broadly categorized into reconstruction-based methods like masked autoencoders (MAE) and discriminative methods such as contrastive learning (CL). Recent empirical observations reveal that MAE and CL capture distinct representations. CL tends to focus on global patterns, while MAE adeptly captures both global and subtle local information simultaneously. Despite a flurry of recent empirical investigations to shed light on this difference, theoretical understanding remains limited, especially on the dominant architecture: vision transformers (ViTs). In this paper, to provide rigorous insights, we model the distribution of visual data by considering two types of spatial features: dominant global features and comparatively minuscule local features and study the impact of imbalance among these features. We analyze the training dynamics of one-layer softmax-based ViTs on both MAE and CL objectives using gradient descent. Our analysis shows that as the degree of feature imbalance varies, ViTs trained with the MAE objective effectively learn both global and local features to achieve near-optimal reconstruction, while the CL-trained ViTs favor predominantly global features, even under mild imbalance. These results provide a theoretical explanation for the different behaviors of MAE and CL observed in prior studies. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Yenho Mudrik, Noga Johnsen, Kyle A. Alagapan, Sankaraleengam Charles, Adam S. Rozell, Christopher J. Machine Learning Center Georgia Institute of Technology United States School of Electrical and Computer Engineering Georgia Institute of Technology United States Coulter Dept. of Biomedical Engineering Emory University Georgia Institute of Technology United States Department of Biomedical Engineering Mathematical Institute for Data Science Center for Imaging Science Kavli Neuroscience Discovery Institute Johns Hopkins University United States

Time-varying linear state-space models are powerful tools for obtaining mathematically interpretable representations of neural signals. For example, switching and decomposed models describe complex systems using latent variables that evolve according to simple locally linear dynamics. However, existing methods for latent variable estimation are not robust to dynamical noise and system nonlinearity due to noise-sensitive inference procedures and limited model formulations. This can lead to inconsistent results on signals with similar dynamics, limiting the model’s ability to provide scientific insight. In this work, we address these limitations and propose a probabilistic approach to latent variable estimation in decomposed models that improves robustness against dynamical noise. Additionally, we introduce an extended latent dynamics model to improve robustness against system nonlinearities. We evaluate our approach on several synthetic dynamical systems, including an empirically-derived brain-computer interface experiment, and demonstrate more accurate latent variable inference in nonlinear systems with diverse noise conditions. Furthermore, we apply our method to a real-world clinical neurophysiology dataset, illustrating the ability to identify interpretable and coherent structure where previous models cannot. © 2024, CC BY-SA.

关键词： State space methods

Citationwalk: Network Representation learning with Scientific Documents

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Lee, Juhyun Park, Sangsung Lee, Junseok Institute of Engineering Research Korea University Seoul02841 Korea Republic of Department of Big Data and Statistics Cheongju University Cheongju28503 Korea Republic of Machine Learning Big Data Institute Korea University Seoul02841 Korea Republic of

A network is a structure that can represent an organic relationship of observations. Network representation learning has the advantage of extracting latent features in a network. In recent years, various algorithms have been developed to embed network representation in a low-dimensional feature space. Conventional algorithms learn a sequence of vertices that are randomly searched from a network and convert a vertex into a vector. This study focused on the representation learning of document networks. Thus, this study proposes a scalable network representation learning algorithm that preserves the structure and content of the document network and reduces data sparsity. To do this, we used the shortest walks to extract a sequence of vertices that reflected semantic similarity from a network. The shortest walk is a method for finding several shortest paths that connect similar vertices. After this, the sequence of vertices was inputted into the language model, assuming that the sequence was a sentence. Experiments were conducted by collecting 29,353 patents, which were scientific documents. The results showed that the proposed algorithm exhibited the lowest error of the tested methods in multi-class classification tasks and link prediction tasks. They also verified that our algorithm employed a smaller sequence of vertices and shorter learning time than other methods. © 2022, The Authors. All rights reserved.

关键词： Semantics

Bayesian inference for data-efficient, explainable, and safe robotic motion planning: A review

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhou, Chengmin Wang, Chao Hassan, Haseeb Shah, Himat Huang, Bingding Fränti, Pasi Machine Learning Group School of Computing University of Eastern Finland JoensuuFI-80100 Finland College of Big Data and Internet Shenzhen Technology University Shenzhen518118 China Machine Learning Group School of Computing University of Eastern Finland JoensuuFI-80100 Finland College of Big Data and Internet Shenzhen Technology University Shenzhen518118 China College of Blockchain industry Chengdu University of Information Technology Chengdu610225 China College of Health Science and Environmental Engineering Shenzhen Technology University Shenzhen518118 China

Bayesian inference has many advantages in robotic motion planning over four perspectives: The uncertainty quantification of the policy, safety (risk-aware) and optimum guarantees of robot’s motions, data-efficiency in reinforcement learning (RL) training, and reducing the sim2real gap when the robot is applied to real-world tasks. However, the application of Bayesian inference in robotic motion planning is lagging behind the comprehensive theory of Bayesian inference. Further, there are no comprehensive reviews to summarize the progress of Bayesian inference to give researchers a systematic understanding in robotic motion planning. This paper first provides the probabilistic theories of Bayesian inference which are the preliminary of Bayesian inference for complex cases. Second, the Bayesian estimation is given to estimate the posterior of policies or unknown functions which are used to compute the policy. Third, the classical model-based Bayesian RL and model-free Bayesian RL algorithms for robotic motion planning are summarized, while these algorithms in complex cases are also analyzed. Fourth, the analysis of Bayesian inference in inverse RL is given to infer the reward functions in a data-efficient manner. Fifth, we systematically present the hybridization of Bayesian inference and RL which is a promising direction to improve the convergence of RL for better motion planning. Sixth, given the Bayesian inference, we present the interpretable and safe robotic motion plannings which are the hot research topic recently. Finally, all algorithms reviewed in this paper are summarized analytically as the knowledge graphs, and the future of Bayesian inference for robotic motion planning is also discussed, to pave the way for data-efficient, explainable, and safe robotic motion planning strategies for practical applications. © 2023, CC BY-NC-ND.

关键词： Reinforcement learning

Cost-Effective Communication in UDN in Indoor and Outdoor Environment via machine learning

学校读者我要写书评

暂无评论

Cost-Effective Communication in UDN in Indoor and Outdoor En...

2023 International Conference on Artificial Intelligence and Knowledge Discovery in Concurrent engineering, ICECONF 2023

作者： Karman, K. Nattar Velmurugan, V. Raju, Kommisetti Murthy Sajana, T. Vijayalakshmi, V. Dhanraj, JoshuvaArockia Department of Artificial Intelligence and Machine Learning Saveetha School of Engineering Tamil Nadu Chennai602105 India Department of Electronics and Communication Engineering Vel Tech Rangarajan and Dr.Sagunthala RandD Institute of Science and Technology Tamil Nadu Chennai600062 India Department of Electronics and Communication Engineering Shri Vishnu Engineering College for Women Andhra Pradesh West Godavari India Department of Artificial Intelligence and Data Science KoneruLakshmaiah Education Foundation Andhra Pradesh Vaddeswaram522502 India Department of Networking and Communications School of Computing SRM Institute of Science and Technology Tamil Nadu Kattankulathur603203 India Department of Mechatronics Engineering Hindustan Institute of Technology and Science Tamil Nadu Chennai603103 India

ISBN: (纸本)9798350334357

In general, applications on a densely populated network are slower. When there are no opportunities to interact with the devices on the network, the user is forced to communicate at some cost. Thus, the inconsistency that exists there increases the cost over that dense network. The single way to evaluate prospect usage is to look at that have used in the earlier period. This paper proposes an upgraded approach to upgrading existing services within the Ultra Dense cloud Network (UDN). In this way the cost for the services available there is calculated in advance and a system is developed to manage it effectively. This proposed method clearly shows that the effective cost can be managed by combining high-costservices and low-costservices separately. This will help to manage the various communication processes to achieve high effectiveness in Ultra Dense cloud Network (UDN). The proposed method achieves 93.28% of Cost-effective data Management.49% of Application log failure, 42 % of system log failure, 98% of network log management, 96% of security log management, 99% cost effective management. © 2023 IEEE.

关键词： Cost effectiveness

Can Multiple Phylogenetic Trees Be Displayed in a Tree-Child Network Simultaneously?

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wu, Yufeng Zhang, Louxin Department of Computer Science and Engineering University of Connecticut Storrs CT06269 United States Department of Mathematics Center for Data Science and Machine Learning National University of Singapore Singapore119076 Singapore

A binary phylogenetic network on a taxon set X is a rooted acyclic digraph in which the degree of each nonleaf node is three and its leaves (i.e. degree-one nodes) are uniquely labeled with the taxa of X. It is tree-child if each nonleaf node has at least one child of indegree one. A set of binary phylogenetic trees may or may not be simultaneously displayed in a binary tree-child network. Necessary conditions for multiple phylogenetic trees being simultaneously displayed in a tree-child network are given here. In particular, it is proved that any two phylogenetic trees can always simultaneously be displayed in some tree-child network on the same taxa set. It is also proved that any set of multiple binary phylogenetic trees can always simultaneously be displayed in some non-binary tree-child network on the same taxa set, where each nonleaf node is of either indegree one and outdegree two or indegree at least two and outdegree *** Codes 05C30 © 2022, CC BY.

关键词： Binary trees

GAIA: A Global, Multi-modal, Multi-scale Vision-Language dataset for Remote Sensing Image Analysis

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zavras, Angelos Michail, Dimitrios Zhu, Xiao Xiang Demir, Begüm Papoutsis, Ioannis Orion Lab School of Rural Surveying and Geoinformatics Engineering National Technical University of Athens Athens15772 Greece Institute of Astronomy Astrophysics Space Applications and Remote Sensing National Observatory of Athens Athens11810 Greece Department of Informatics and Telematics Harokopio University of Athens Athens17676 Greece Chair of Data Science in Earth Observation Technical University of Munich Munich80333 Germany Munich Center for Machine Learning Munich80333 Germany Faculty of Electrical Engineering and Computer Science Technische Universität Berlin Berlin10623 Germany BIFOLD - Berlin Institute for the Foundations of Learning and Data Berlin10623 Germany

The continuous operation of Earth-orbiting satellites generates vast and ever-growing archives of Remote Sensing (RS) images. Natural language presents an intuitive interface for accessing, querying, and interpreting the data from such archives. However, existing Vision-Language Models (VLMs) are predominantly trained on web-scraped, noisy image-text data, exhibiting limited exposure to the specialized domain of RS. This deficiency results in poor performance on RS-specific tasks, as commonly used datasets often lack detailed, scientifically accurate textual descriptions and instead emphasize solely on attributes like date and location. To bridge this critical gap, we introduce GAIA, a novel dataset designed for multi-scale, multi-sensor, and multi-modal RS image analysis. GAIA comprises of 205,150 meticulously curated RS image-text pairs, representing a diverse range of RS modalities associated to different spatial resolutions. Unlike existing vision-language datasets in RS, GAIA specifically focuses on capturing a diverse range of RS applications, providing unique information about environmental changes, natural disasters, and various other dynamic phenomena. The dataset provides a spatially and temporally balanced distribution, spanning across the globe, covering the last 25 years with a balanced temporal distribution of observations. GAIA’s construction involved a two-stage process: (1) targeted web-scraping of images and accompanying text from reputable RS-related sources, and (2) generation of five high-quality, scientifically grounded synthetic captions for each image using carefully crafted prompts that leverage the advanced vision-language capabilities of GPT-4o. We also release an automated processing framework developed for this purpose, enabling the broader research community to generate captions for RS images using the web-crawled image-text data. Our extensive experiments, including fine-tuning of CLIP and BLIP2 models, demonstrate that GAIA significan

关键词： Visual languages

Beyond Words: Exploring Emotion Detection in Speech Using Sound

学校读者我要写书评

暂无评论

Beyond Words: Exploring Emotion Detection in Speech Using So...

Emerging Technology (INCET), International Conference for

作者： Ruchika Vaidya Sarthak Gaurkhede Rahul Dattangire K.T.V Redddy Utkarsha Pachraney Divya Biradar Artificial intelligence And Machine Learning Datta Meghe Institute of Higher Education and Research (DU) Wardha Maharashtra India Data Engineering Publicis Sapient Houston Texas USA Datta Meghe Institute of Higher Education and Research (DU) Wardha Maharashtra India Computer Science University of Texas at Arlington Arlignton Texas USA

ISBN: (数字)9798350361155

ISBN: (纸本)9798350361162

Speech emotion recognition (SER) has the possible to revolutionize human-computer interaction and numerous other fields. This paper explores the application of deep learning, mostly Long Short-Term Memory (LSTM) networks, for SER by the Toronto Speech Emotion Set (TESS) dataset. TESS data undergoes rigorous pre-processing, including normalization and feature extraction, to prepare it for the LSTM model. This model choice leverages its ability to capture essential long-term dependencies inside the audio data. Through careful selection and optimization of hyperparameters, the LSTM network architecture is fine-tuned to achieve optimal performance. The training process employs optimizers and a loss function to guide the model in learning the complicated relationships between extracted features and conforming emotions. To comprehensively measure the model's efficiency, various metrics are used, together with accuracy, precision, recall, and F1-score. This research underwrites to the advancement of SER by representing the efficiency of deep learning, specifically LSTMs, on the TESS dataset. The findings not only offer valuable insights into model selection, data pre-processing, and performance calculation but also cover the technique for further exploration of deep learning in SER applications.

关键词： Deep learning Training Emotion recognition Accuracy Training data Speech recognition Feature extraction