检索结果-内蒙古大学图书馆

Natural Language Processing of Text-Based Metrics for Image Captioning 1

International Conference on Intelligent Systems and Sustainable Computing, ICISSC 2021

作者： Sengan, Sudhakar Sagar, P. Vidya Saravanan, N.P. Amarendra, K. Subburaj, Arjun Maheswari, S. Rangasamy, Rajasekar Department of Computer Science and Engineering PSN College of Engineering and Technology Tamil Nadu Tirunelveli627152 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation A.P. Vaddeswaram India Department of Computer Science and Engineering Kongu Engineering College Tamil Nadu Perundurai638060 India Tranxit Technology Solutions Pvt. Ltd. Tamil Nadu Chennai India Department of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Chennai India Department of Computer Science and Engineering-AI & ML School Engineering Malla Reddy University Hyderabad India

ISBN: (数字)9789811900112

ISBN: (纸本)9789811900105

A rapidly increasing interest has been focused on natural language processing and computer vision study by automatically producing descriptive sentences for images in present trends. Image processing is a success factor, especially involving somaticized image knowledge and creating reliable, appropriately organized explanation phrases. In this paper, a dynamic program that uses the VCG16 platform to develop image descriptions and a long short-term memory (LSTM) to contain appropriate words with generated text keywords successfully is proposed. This paper determines the NLP method’s usefulness using Flickr8 K-statistical models and demonstrates that their model delivers accurate performance compared to the Bleu metric. The Bleu metric is an automated system for measuring a machine translation’s performance by monitoring the effectiveness of text transformed from natural to other languages. The results have been justified with images that satisfy the NLP algorithm. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Leveraging Large Language Models for Biomedical Knowledge Graph Construction and Querying: An Advanced NLP Approach 25

Leveraging Large Language Models for Biomedical Knowledge Gr...

引用

Companion Proceedings of the ACM on Web Conference 2025

作者： Suramya Jadhav Suki Perumal Yasmin Tadavi Bikshita Dash Srinivasan Parthiban Computer Engineering Department Pune Institute of Computer Technology Pune India Department of CSE (AI & ML) PES University Bangalore India Department of Data Science and Engineering Indian Institute of Science Education and Research Bhopal India Aarupadai Veedu Medical College & Hospital Centre for AI in Medicine Vinayaka Missions Research Foundation Puducherry India

ISBN: (纸本)9798400713316

This paper introduces a novel methodology for constructing a comprehensive biomedical knowledge graph by applying advanced Natural Language Processing (NLP) techniques. By leveraging Large Language Models (LLMs) and a multifaceted prompt engineering approach, we effectively perform Named Entity Recognition (NER) and Relation Extraction (RE) on biomedical literature, targeting entities such as diseases, drugs, proteins, procedures, and symptoms. Our methodology incorporates eight distinct prompt engineering strategies for NER and a standardized approach for RE, facilitating the extraction of intricate inter-entity relationships. The resulting knowledge graph amalgamates diverse data sources into a unified framework, enabling efficient querying, visualization, and analysis of biomedical information. Furthermore, we present an innovative query processing pipeline that integrates GPT-3.5 turbo with the knowledge graph, allowing users to interact with the graph through natural language. This integrated system empowers the discovery of novel correlations, accelerating scientific research and fostering interdisciplinary collaboration. This represents a substantial contribution to the field of biomedical knowledge graph construction, offering a robust platform for accelerating scientific discovery and informing clinical decision-making.

关键词： knowledge graphs

来源：评论

学校读者我要写书评

暂无评论

Enhanced Large Language Models

Enhanced Large Language Models

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： J.R.V. Jeny G. Bharath Babu S. Jaganmohan Reddy N. Muthukumaran K. Abhiram Department of Computer Science and Engineering (AI&ML) Vignan Institute of Technology and Science Nalgonda Telangana Department of ECE Centre for Computational Imaging and Machine Vision Sri Eshwar College of Engineering Coimbatore Tamil Nadu India

ISBN: (数字)9798350359299

ISBN: (纸本)9798350359305

This work studies ways for improving the effectiveness of a language model in creating and understanding dialogue summaries. Two primary approaches are investigated, in the Complete Fine-Tuning step, a pre-trained FLAN-T5 model is fine-tuned using a dataset of dialog-summary pairs. The dataset is pre-processed to provide explicit instructions to the model, and the fine-tuning process involves training the entire model on the dataset. Qualitative and quantitative evaluations are then conducted to assess the effectiveness of the fine-tuned model in generating summaries. In the PEFT phase, a more computationally efficient method is employed, utilizing Low-Rank Adaptation (LoRA) to train a new layer/parameter adapter while keeping the underlying FLAN-T5 model frozen. This approach significantly reduces computational resources compared to Complete Fine-Tuning while maintaining comparable performance. The resulting model, equipped with the PEFT adapter, is evaluated qualitatively and quantitatively to measure its summarization capabilities. Both approaches sheds light on the compromises between computing efficiency and model performance.

关键词： Training Measurement Adaptation models Generative ai Computational modeling Natural languages Information retrieval

来源：评论

学校读者我要写书评

暂无评论

Instagram Reach Analysis using Machine Learning Algorithms

Instagram Reach Analysis using Machine Learning Algorithms

引用

Computational Intelligence for Security, Communication and Sustainable Development (CISCSD), International Conference on

作者： Abhinav G Bhat Tarun Rao K Shridhar B. Devamane Udayaprasad P K Ravindranath R. C Lakshmikantha G C Department of Computer Science Global Academy of Technology Bengaluru Karnataka India Department of AI & ML Global Academy of Technology Bengaluru Karnataka India

ISBN: (数字)9798350365405

ISBN: (纸本)9798350365412

One of the most widely used social media platforms right now is Instagram. Instagram is used professionally by those who want to promote their brands, develop their portfolios and blogs, and produce various types of content. Instagram is a well-known program used by millions of users in multiple niches, and it is constantly evolving to serve both users and content creators better. Nevertheless, as this fluctuates, it impacts the audience for our postings, which has a long-term impact on us. So, a content producer must examine the analytics of their Instagram reach if they hope to succeed on the platform over the long term.

关键词： Machine learning algorithms Social networking (online) Forestry Boosting Web sites Multimedia communication Security Sustainable development Portfolios Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

Fast-Hubert: an Efficient Training Framework for Self-Supervised Speech Representation Learning

Fast-Hubert: an Efficient Training Framework for Self-Superv...

引用

2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023

作者： Yang, Guanrou Ma, Ziyang Zheng, Zhisheng Song, Yakun Niu, Zhikang Chen, Xie Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence Ai Institute X-LANCE Lab Department of Computer Science and Engineering China

ISBN: (纸本)9798350306897

Recent years have witnessed significant advancements in self-supervised learning (SSL) methods for speech-processing tasks. Various speech-based SSL models have been developed and present promising performance on a range of downstream tasks including speech recognition. However, existing speech-based SSL models face a common dilemma in terms of computational cost, which might hinder their potential application and in-depth academic research. To address this issue, we first analyze the computational cost of different modules during HuBERT pre-training and then introduce a stack of efficiency optimizations, which is named Fast-HuBERT in this paper. The proposed Fast-HuBERT can be trained in 1.1 days with 8 V100 GPUs on the Librispeech 960 h benchmark, without performance degradation, resulting in a 5.2x speedup, compared to the original implementation. Moreover, we explore two well-studied techniques in the Fast-HuBERT and demonstrate consistent improvements as reported in previous work.11The code for Fast-HuBERT training is available at https://***/yanghaha0908/FastHuBERT © 2023 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Performance comparison of machine learning algorithms for coronary heart disease prediction

Performance comparison of machine learning algorithms for co...

引用

Computational Intelligence for Security, Communication and Sustainable Development (CISCSD), International Conference on

作者： Bharath RC Aneesh RT Aniruddha GJ Shridhar B. Devamane Ravindranath R.C Lakshmikantha G C Department of Computer Science Global Academy of Technology Bengaluru Karnataka India Department of AI & ML Global Academy of Technology Bengaluru Karnataka India

ISBN: (数字)9798350365405

ISBN: (纸本)9798350365412

The algorithms used in these machine learning models are quite straightforward and easy to understand, and they may produce predictions. These models have numerous business and scientific applications. Machine Learning model predictions are employed across many disciplines, including biology, behavioural sciences, environmental sciences, social sciences, and economics. We have discussed both the theoretical and practical elements in this paper.

关键词： Heart Machine learning algorithms Biological system modeling Social sciences Predictive models Prediction algorithms Security Sustainable development Regression tree analysis Random forests

来源：评论

学校读者我要写书评

暂无评论

Disconnected Emerging Knowledge Graph Oriented Inductive Link Prediction 39

Disconnected Emerging Knowledge Graph Oriented Inductive Lin...

引用

39th IEEE International Conference on Data engineering, ICDE 2023

作者： Zhang, Yufeng Wang, Weiqing Yin, Hongzhi Zhao, Pengpeng Chen, Wei Zhao, Lei Soochow University School of Computer Science and Technology China Monash University Department of Data Science and Ai Australia The University of Queensland School of Information Technology and Electrical Engineering Australia

ISBN: (纸本)9798350322279

Inductive link prediction (ILP) is to predict links for unseen entities in emerging knowledge graphs (KGs), considering the evolving nature of KGs. A more challenging scenario is that emerging KGs consist of only unseen entities without any edge connected to original KGs, called as disconnected emerging KGs (DEKGs). Existing studies for DEKGs only focus on predicting enclosing links, i.e., predicting links inside the emerging KG. The bridging links, which carry the evolutionary information from the original KG to DEKG, have not been investigated by previous work so far. To fill in the gap, we propose a novel model entitled DEKG-ILP (Disconnected Emerging Knowledge Graph Oriented Inductive Link Prediction) that consists of the following two components. (1) The module CLRM (Contrastive Learning-based Relation-specific Feature Modeling) is developed to extract global relation-based semantic features that are shared between original KGs and DEKGs with a novel sampling strategy. (2) The module GSM (GNN-based Subgraph Modeling) is proposed to extract the local subgraph topological information around each link in KGs. The extensive experiments conducted on several benchmark datasets demonstrate that DEKG-ILP has obvious performance improvements compared with state-of-the-art methods for both enclosing and bridging link prediction. © 2023 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

The tale of two sides in the 2019 anti-CAA protest—An analytical framework

引用

International Journal of Information Management Data Insights 2024年第2期4卷

作者： Das, Bhaskarjyoti Ragothaman, Krithika Kesari, Raghav T. Sudarshan, T.S.B. Department of Computer Science and Engineering in AI & ML PES University Banashankari Stage III Bengaluru 560085 India Department of Computer Science and Engineering PES University Banashankari Stage III Bengaluru 560085 India

The 2019 anti-CAA protest in India witnessed massive Twitter participation from people on both sides. It was unique compared to most online social movements that showcase people's movements against authority. The article offers a framework for a big data-driven outside-in analysis of such online social movements. Unlike most existing research focusing on a particular aspect of such a movement, the framework presented examines mobilization and counter-mobilization from various angles. The work systematically juxtaposes the proponents and opponents using statistical analysis, text mining, and graph analysis techniques. Different aspects such as users, content, themes and focus of the conversations, conversational patterns, instrumentation of virality, leadership styles, emotions, and toxicity of the discourse have been considered. The study also examines them as types of frame alignment effort as per Frame Alignment Theory. The framework proposed by this work can be successfully employed to understand any future online social movement and any inductive research using user-generated Big Data. © 2024 The Authors

关键词： Analytical framework Conversation patterns Emotion and toxicity Frame alignment Hashtag virality Leadership style Lexical divergence Online social movement

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Machine Learning Algorithms for Predicting Customer Churn: Analyzing Sequential, Random Forest, and Decision Tree Classifier Models

A Comparative Study of Machine Learning Algorithms for Predi...

引用

Electronics and Sustainable Communication Systems (ICESC), 2020 International Conference on

作者： Ratnam Dodda C. Raghavendra Marpu Aashritha Hima Varshini Macherla Anusha Reddy Kuntla Department of CSE (AI&ML) CVR College of Engineering Hyderabad India Department of CSE (DS) CVR College of Engineering Hyderabad India Department of Computer Science and Information Technology CVR College of Engineering Hyderabad India

ISBN: (数字)9798350379945

ISBN: (纸本)9798350379952

Predicting customer churn is vital for businesses aiming to retain their customer base and enhance profitability. This study investigates the effectiveness of three prominent machine learning algorithms Sequential, Random Forest, and Decision Tree Classifier in forecasting customer churn. Utilizing a dataset encompassing historical customer information such as demographics, transaction records, and interaction patterns, we preprocess the data by addressing missing values, encoding categorical variables, and scaling numerical features. Subsequently, each model is trained on the processed dataset, and their performance is assessed using accuracy as the evaluation metric. Our findings demonstrate promising predictive capabilities, with the Sequential model achieving an accuracy score of 94%, followed by Random Forest with 92%, and Decision Tree Classifier with 91%. Additionally, we conduct a comparative analysis of these models, focusing on interpretability, computational complexity, and robustness. While the Sequential model excels in predictive accuracy by capturing temporal dependencies in sequential data, Random Forest and Decision Tree Classifiers offer simplicity and interpretability, catering to scenarios where model transparency is paramount.

关键词： Analytical models Accuracy Machine learning algorithms Computational modeling Predictive models Prediction algorithms Data models Numerical models Decision trees Random forests

来源：评论

学校读者我要写书评

暂无评论

Hybrid Optimization Algorithm to Mitigate Phishing URL Attacks In Smart Cities 3

Hybrid Optimization Algorithm to Mitigate Phishing URL Attac...

引用

3rd International Conference on Innovative Practices in Technology and Management, ICIPTM 2023

作者： Sujatha, G. Ayyannan, Manimuthu Priya, S. Gayathri Arun, V. Arularasan, A.N. Kumar, M Jogendra Sri Venkateswara College of Engineering Department of Electronics and Communication Andhra Pradesh Tirupati India AI/ML and Data Expert San FranciscoCA United States R. M. D. Engineering College Department of Electronics and Communication Tamil Nadu Kavaraipettai India Madanapalle Institute of Technology Department of Computer Science &engineering Andhra Pradesh Madanapalle India Panimalar Engineering College Department of Artificial Intelligence &data Science Tamil Nadu Chennai India Koneru Lakshmaiah Education Foundation Department of Computer Science Andhra Pradesh Vaddeswaram India

ISBN: (纸本)9798350336238

To improve the detection of phishing sites, this proposal introduces feature weights for intelligent phishing site detection based on hybrid bio-inspired algorithms. The proposed approach uses Gray Wolf Optimization (GWO) and Firefly Algorithm (FF), which examines a wide range of website attributes, to more precisely identify phishing sites. Then employs Artificial Neural Network (ANN) to classify different website elements according to the importance of each component in differentiating between legitimate and phishing websites using bioinspired-based recommended site feature weights. According to experimental findings, the suggested hybrid bioinspired-based feature weighting greatly improved classification accuracy, true positive (TPR), and negative rates (TNR), as well as precision and F1 score. Phishing is an online crime that entails the gathering of private information like passwords, account numbers, and credit card numbers. Attackers use alluring URLs to entice phony website visitors. Recently, Artificial Intelligence-based phishing detection has seen some success, and in this study, ANN was used to detect phishing. This ANN classifier may make phishing websites simpler to spot. However, it has been shown that the effectiveness of detection can be increased by applying a genetic algorithm to improve feature selection. © 2023 IEEE.

关键词： Websites

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：