检索结果-内蒙古大学图书馆

Optimal trained ensemble of classification model for satellite image classification

Multimedia Tools and Applications 2025年第7期84卷 3745-3766页

作者： Singh, Sarabjeet Kundra, Harish Kundra, Sheetal Pratima, P. Venkata Devi, M. V. Anjana Kumar, Sushil Hassan, Mariya Department of Computer Science and Engineering Chandigarh College of Engineering and Technology Chandigarh160019 India Department of Computer Science and Engineering Guru Nanak Institutions Technical Campus Ranga Reddy District Telangana Ibrahimpatnam501506 India Department of Artificial Intelligence and Data Science Guru Nanak Institute of Technology Ranga Reddy District Telangana Ibrahimpatnam501506 India Department of Computer Science and Engineering Central University of Haryana Jant-Pali Mahendergarh123031 India

Satellite image classification is the most significant remote sensing method for computerized analysis and pattern detection of satellite data. This method relies on the image's diversity structures and necessitates a thorough validation of the training data using the chosen classification algorithm. The classifying of remotely sensed images refers to the process of classifying pixels into a fixed set of distinct classes based on their data values. The pixel is categorized into that class if it complies with a specific set of requirements. A new SIC scheme is suggested in this work, where, Contrast limited adaptive histogram equalization (CLAHE) is deployed for pre-processing the image. Further, statistical features, Vegetation Indices (VI) and Improved Hybrid Vegetation Index (IHVI) are extracted from the preprocessed image. Then, we deploy 2 phase classification process for classifying the image. In the first phase, Bi-Directional Gated Recurrent Unit (BI-GRU), Convolutional Neural Network (CNN) and Deep Max Out (DMO) are used. In 2nd phase, optimized RNN is used for determining the final classification result. Also, the training of the model is done by the new Chaotic Opposition Behavior Improvised Coot Algorithm (COBI-CA) optimization via tuning the optimal weights. The COOT method has been enhanced and is now the suggested algorithm. Lastly, we conduct an analysis to compare the suggested Satellite Image Classification (SIC) model's performance to the traditional approaches in terms of statistical analysis, precision, accuracy, and error measure. In comparison to other conventional methods, the accuracy of the suggested model is 97%. © This is a U.S. Government work and not under copyright protection in the US;foreign copyright protection may apply 2024.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

SAMPLING-FREE INFERENCE FOR AB-INITIO POTENTIAL ENERGY SURFACE NETWORKS 11

SAMPLING-FREE INFERENCE FOR AB-INITIO POTENTIAL ENERGY SURFA...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Gao, Nicholas Günnemann, Stephan Department of Computer Science Munich Data Science Institute Technical University of Munich Germany

Recently, it has been shown that neural networks not only approximate the ground-state wave functions of a single molecular system well but can also generalize to multiple geometries. While such generalization significantly speeds up training, each energy evaluation still requires Monte Carlo integration which limits the evaluation to a few geometries. In this work, we address the inference shortcomings by proposing the Potential learning from ab-initio Networks (PlaNet) framework, in which we simultaneously train a surrogate model in addition to the neural wave function. At inference time, the surrogate avoids expensive Monte-Carlo integration by directly estimating the energy, accelerating the process from hours to milliseconds. In this way, we can accurately model high-resolution multi-dimensional energy surfaces for larger systems that previously were unobtainable via neural wave functions. Finally, we explore an additional inductive bias by introducing physically-motivated restricted neural wave function models. We implement such a function with several additional improvements in the new PESNet++ model. In our experimental evaluation, PlaNet accelerates inference by 7 orders of magnitude for larger molecules like ethanol while preserving accuracy. Compared to previous energy surface networks, PESNet++ reduces energy errors by up to 74 %. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Wave functions

来源：评论

学校读者我要写书评

暂无评论

Language Identification System: Employing ReLu for India's Regional Languages (ReLu) 2

Language Identification System: Employing ReLu for India's R...

引用

2nd International Conference for Advancement in Technology, ICONAT 2023

作者： Saini, Lekhraj Defence Institute of Advanced Technology School of Computer Science and Data Science Pune India

ISBN: (纸本)9781665475174

In this paper, I provide a model for language identification that makes use of neural networks. The approach is intended to distinguish between Indian regional and dialectal languages. Individuals of Indian descent are the target population for this model. I train the model using a variety of data sources, including corpora of written and spoken material in a variety of languages. In addition, I use a variety of additional data sources. As a result, we can train the model to be more accurate. When I compare the performance of our model to that of a naive Bayes classifier, I find that the results produced by our model are superior to those produced by the naive Bayes classifier. This is because our model considers more information than the naïve Bayes classifier. The ReLu activation function is employed on each neuron throughout our simulation, and the neural network design comprises several layers. Each neuron receives the ReLu activation function. This allows the model to capture the relationships and correlations that exist between the input data, which improves its capacity to recognize the language employed in a specific sentence. Furthermore, our technology can deal with ambiguous cases, such as sentences written in the devnagri script, which is utilized in a number of Indian languages. This is a benefit provided by our software. Using our system has several advantages, and this is only one of them. © 2023 IEEE.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

SEGMENT+: Long Text Processing with Short-Context Language Models

SEGMENT+: Long Text Processing with Short-Context Language M...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Shi, Wei Li, Shuang Yu, Kerun Chen, Jinglei Liang, Zujie Wu, Xinhui Qian, Yuxi Wei, Feng Zheng, Bo Liang, Jiaqing Chen, Jiangjie Xiao, Yanghua Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China Columbia University United States MYbank Ant Group China School of Data Science Fudan University China

ISBN: (纸本)9798891761643

There is a growing interest in expanding the input capacity of language models (LMs) across various domains. However, simply increasing the context window does not guarantee robust performance across diverse long-input processing tasks, such as understanding extensive documents and extracting detailed information from lengthy and noisy data. In response, we introduce SEGMENT+, a general framework that enables LMs to handle extended inputs within limited context windows efficiently. SEGMENT+ utilizes structured notes and a filtering module to manage information flow, resulting in a system that is both controllable and interpretable. Our extensive experiments across various model sizes, focusing on long-document question-answering and Needle-in-a-Haystack tasks, demonstrate the effectiveness of SEGMENT+ in improving performance. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Graph Augmentation Empowered Contrastive Learning for Recommendation

引用

ACM Transactions on Information Systems 2025年第2期43卷 1-27页

作者： Xu, Lixiang Liu, Yusheng Xu, Tong Chen, Enhong Tang, Yuanyan School of Artificial Intelligence and Big Data Hefei University Hefei China State Key Laboratory of Cognitive Intelligence School of Computer Science and Technology University of Science and Technology of China Hefei China Zhuhai UM Science and Technology Research Institute FST University of Macau China

The application of contrastive learning (CL) to collaborative filtering (CF) in recommender systems has achieved remarkable success. CL-based recommendation models mainly focus on creating multiple augmented views by employing different graph augmentation methods and utilizing these views for self-supervised learning. However, current CL methods for recommender systems usually struggle to fully address the problem of noisy data. To address this problem, we propose the Graph Augmentation Empowered Contrastive Learning (GAECL) for recommendation framework, which uses graph augmentation based on topological and semantic dual adaptation and global co-modeling via structural optimization to co-create contrasting views for better augmentation of the CF paradigm. Specifically, we strictly filter out unimportant topologies by reconstructing the adjacency matrix and mask unimportant attributes in nodes according to the PageRank centrality principle to generate an augmented view that filters out noisy data. Additionally, GAECL achieves global collaborative modeling through structural optimization and generates another augmented view based on the PageRank centrality principle. This helps to filter the noisy data while preserving the original semantics of the data for more effective data augmentation. Extensive experiments are conducted on five datasets to demonstrate the superior performance of our model over various recommendation models. © 2025 Copyright held by the owner/author(s).

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

GAN-IE: Generative Adversarial Network for Information Extraction with Limited Annotated data 1

引用

24th International Conference on Web Information Systems Engineering, WISE 2023

作者： Talukder, Ahmed Shoeb Nayak, Richi Bashar, Md Abul Centre for Data Science School of Computer Science Queensland University of Technology Brisbane Australia

ISBN: (数字)9789819972548

ISBN: (纸本)9789819972531

Extracting valuable information from a large corpus of unstructured data poses a formidable challenge in many applications. Transformer-based architectures e.g. BERT, employing transfer learning techniques, have exhibited promising results across diverse NLP tasks. Nonetheless, the practical implementation of these models presents a significant hurdle given the substantial demand for annotated data during the training phase. In this paper, we present GAN-IE, a novel GAN-based model architecture, designed specifically for information extraction from unstructured textual data while accounting for limited annotated resources. In a generative adversarial setting, GAN-IE leverages BERT’s rich semantic and contextual knowledge obtained from unlabelled data while fine-tuning. Experimental results show that GAN-IE achieves a level of accuracy that surpasses the current state-of-the-art models when trained using a fraction of labelled data (∼ 100–200 annotated samples). © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Identification of domain-specific euphemistic tweets using clustering

引用

International Journal of Information Technology (Singapore) 2024年第1期16卷 21-31页

作者： Devi, Maibam Debina Saharia, Navanath Data Engineering Lab Department of Computer Science & Engineering IIIT Senapati Manipur Imphal 795002 India

Social media platforms (SMPs) are frequently utilised as a readily accessible and comprehensive medium for expressing personal opinions nowdays. The use of euphemism, a linguistic strategy in which the underlying feeling of expressive content is veiled by the use of mild language, has been a longtime practise in the realm of SMPs for the purpose of reducing harshness or to discuss sensitive topics [1]. The identification of masked contents [2] in euphemism is challenging due to their inherent nature. This study presents a proposed identification mechanism aimed at detecting domain-specific euphemisms through the utilisation of clustering techniques. The pattern categorization feature is created utilising domain-specific lexical features combined with frequency-based features. In order to identify the most suitable match, the hybrid feature extraction algorithms incorporate uni-gram and bi-gram features dependent on frequency based feature, in conjunction with a lexicon. The objective of the dimension reduction phase is to address the issue of sparsity and to identify the most significant words for each sample in order to classify them into different domains using centroid and density-based clustering techniques. The DBSCAN algorithm is employed with an epsilon value of 2.5 and a minimum number of points set to 6, resulting in the identification of 7 distinct clusters. To calculate the optimal value for k in the K-means algorithm, the Silhouette score is utilised. The clusters that were obtained are examined by manual means. We compare our model to FLUTE dataset with epsilon value of 0.2, minpoints of 5 for DBSCAN, and obtain validation score of 0.55. The DBSCAN clustering algorithm generates distinct clusters that extend beyond the scope of the inquiry domain. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： DBSCAN Domain-specific euphemistic text Euphemism K-means Silhouette score

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Privacy Protection Model in Advanced Metering Infrastructure Based on Cloud and Fog Assistance

引用

computers, Materials & Continua 2024年第8期80卷 3193-3219页

作者： Linghong Kuang Wenlong Shi Jing Zhang School of Computer Science and Mathematics Fujian University of TechnologyFuzhou350118China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fuzhou350118China

The Advanced Metering Infrastructure(AMI),as a crucial subsystem in the smart grid,is responsible for measuring user electricity consumption and plays a vital role in communication between providers and ***,with the advancement of information and communication technology,new security and privacy challenges have emerged for *** address these challenges and enhance the security and privacy of user data in the smart grid,a Hierarchical Privacy Protection Model in Advanced Metering Infrastructure based on Cloud and Fog Assistance(HPPM-AMICFA)is proposed in this *** proposed model integrates cloud and fog computing with hierarchical threshold encryption,offering a flexible and efficient privacy protection solution that significantly enhances data security in the smart *** methodology involves setting user protection levels by processing missing data and utilizing fuzzy comprehensive analysis to evaluate user importance,thereby assigning appropriate protection ***,a hierarchical threshold encryption algorithm is developed to provide differentiated protection strategies for fog nodes based on user IDs,ensuring secure aggregation and encryption of user *** results demonstrate that HPPM-AMICFA effectively resists various attack strategies while minimizing time costs,thereby safeguarding user data in the smart grid.

关键词： AMI cloud and fog assistance fuzzy comprehensive analysis hierarchical threshold encryption

来源：评论

学校读者我要写书评

暂无评论

Achieving dynamic privacy measurement and protection based on reinforcement learning for mobile edge crowdsensing of IoT

引用

Digital Communications and Networks 2024年第2期10卷 380-388页

作者： Renwan Bi Mingfeng Zhao Zuobin Ying Youliang Tian Jinbo Xiong Fujian Provincial Key Laboratory of Network Security and Cryptology College of Computer and Cyber SecurityFujian Normal UniversityFuzhou350117China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic TechnologyGuilin541004China Faculty of Data Science City University of Macao999078MacaoChina State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang550025China

With the maturity and development of 5G field,Mobile Edge CrowdSensing(MECS),as an intelligent data collection paradigm,provides a broad prospect for various applications in ***,sensing users as data uploaders lack a balance between data benefits and privacy threats,leading to conservative data uploads and low revenue or excessive uploads and privacy *** solve this problem,a Dynamic Privacy Measurement and Protection(DPMP)framework is proposed based on differential privacy and reinforcement ***,a DPM model is designed to quantify the amount of data privacy,and a calculation method for personalized privacy threshold of different users is also ***,a Dynamic Private sensing data Selection(DPS)algorithm is proposed to help sensing users maximize data benefits within their privacy ***,theoretical analysis and ample experiment results show that DPMP framework is effective and efficient to achieve a balance between data benefits and sensing user privacy protection,in particular,the proposed DPMP framework has 63%and 23%higher training efficiency and data benefits,respectively,compared to the Monte Carlo algorithm.

关键词： Mobile edge crowdsensing Dynamic privacy measurement Personalized privacy threshold Privacy protection Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

FCIGAN: A Three-dimensional Ink Rendering Brushwork Based on Generative Adversarial Network

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第3期9卷 1348-1358页

作者： Wang, Qinghua Lin, Wenru Lan, Wei Huang, Jingwei Chen, Yang Long, Xinling Zheng, Lujia Huang, Huilong Zhang, Fuquan School of Computer and Data Science Minjiang University Fuzhou University Town No.200 Xiyuangong Road Fuzhou350108 China Fujian Province University Fuzhou350300 China College of Computer and Big Data Fuzhou University Fuzhou China

Three-dimensional ink rendering is a NPR (Non-Photorealistic rendering) art style, widely used in a range of fields, including gaming and ***, CycleGAN is a standard image transformation model, however, it prefers Western painting methods, resulting in less-than-ideal ink rendering effects. As a result, this investigation focuses on the characteristics of ink painting by merging attention processes with three-dimensional depth information. It emphasizes differences in ink color depth to depict the relationship between distance and three-dimensional perception of things in the picture. It also makes use of methods like line thickness and curves to show the contours and textures of things. Additionally, to make the picture as close to the real traditional Chinese ink painting as possible, we use the thickness and bending of lines to show the outline and texture of objects, and highlight the key points or depict some details in the picture by leaving blank. This method is named FCIGAN (Freehand Chinese Ink Generative Adversarial Network). We have also gathered and created a matching dataset called FCI Images to aid in the experiment’s smooth progression. In conclusion, the experimental results show that, the FCIGAN approach suggested in this research has much better performance when compared to conventional techniques and may be used more effectively in the 3D rendering field. © 2024, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Generative adversarial networks

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：