检索结果-内蒙古大学图书馆

Question classification task based on deep learning models with self-attention mechanism

Multimedia Tools and Applications 2025年第10期84卷 7777-7806页

作者： Mondal, Subhash Barman, Manas Nag, Amitava Computer Science and Engineering Central Institute of Technology Kokrajhar Assam Kokrajhar India Computer Science and Engineering [AI & ML Dayananda Sagar University Karnataka Bengaluru India

Question classification (QC) is a process that involves classifying questions based on their type to enable systems to provide accurate responses by matching the question type with relevant information. To understand and respond to natural language questions posed by humans, machine learning models or systems must comprehend the type of information requested, which can often be inferred from the structure and wording of the question. The high dimensionality and sparse nature of text data lead to challenges for text classification. These tasks can be improved using deep learning (DL) approaches to process complex patterns and features within input data. By training on large amounts of labeled data, deep learning algorithms can automatically extract relevant features and representations from text, resulting in more accurate and robust classification. This study utilizes a dataset comprising 5452 instances of questions and six output labels and uses two different word embedding techniques, like GloVe and Word2Vec, tested on the dataset using three deep learning models, LSTM, BiLSTM, and GRU, followed by a convolution layer. Additionally, a self-attention layer is included, which helps the model to focus on more relevant information when making predictions. Finally, an analytical discussion of the proposed models and their performance results provide insight into how GloVe and Word2Vec perform on the above-mentioned models. The GloVe embedding outperforms by achieving 97.68% accuracy and a moderate loss of 16.98 with the GRU model. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

CAml: Cryptographic-Based Cloud Security for Healthcare Data with Machine Learning Technique

引用

Recent Patents on engineering 2025年第2期19卷 26-40页

作者： M.H, Chaithra Vagdevi, S. Department of Computer Science and Engineering REVA University & Research Scholar Affiliated to Visvesvaraya Technological University Karnataka Belagavi India Department of AI & ML City Engineering College Karnataka Bangalore India

Background: The Cloud model is one of the most realistic frameworks with a vast range of social networking interactions. In medical data, security is a major constraint as it incorporates information about the patients. The cloud environment subjected to mobility and openness is exposed to security issues and limits authorization levels for data transmission. Objective: This patent paper aims to propose a security model for attack prevention within the healthcare environment. Methods: The proposed Cryptographic Attribute-based Machine Learning (CAml) scheme incorporates three stages. Initially, the homomorphic encryption escrow is performed for secure data transmission in the cloud. Secondly, the information of the users is evaluated based on the consideration of users' authorization. The authorization process for the users is carried out with the attribute-based ECC technique. Finally, the ml model with the classifier is applied for the detection and classification of attacks in the medical network. Results: The detected attack is computed and processed with the CNN model. Simulation analysis is performed for the proposed CAml with conventional ANN, CNN, and RNN models. The simulation analysis of proposed CAml achieves a higher accuracy of 0.96 while conventional SVM, RF, and DT achieve an accuracy of 0.82, 0.89 and 0.93, respectively. Conclusion: With the analysis, it is concluded that the proposed CAml model achieves higher classification accuracy for attack detection and prevention in the cloud computing environment. © 2025 Bentham science Publishers.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Meta-Learning-Based Multimodal Fake News Detection 5th

Meta-Learning-Based Multimodal Fake News Detection

引用

5th International Conference on Computing and Network Communications, CoCoNet 2023

作者： Varun, M.S. Bhattacharjee, Ishaan Venkatesha, Pratheek Karike Sathvik, A. Pramath, S. Das, Bhaskarjyoti Department of Computer Science and Engineering PES University Karnataka Bengaluru India Department of Computer Science and Engineering in AI and ML PES University Karnataka Bengaluru India

ISBN: (纸本)9789819745395

In the contemporary digital era, spreading false information via social media and Internet platforms poses a significant challenge. Not only the data has become increasingly multimodal, lack of sufficient labeled data due to prohibitive labeling costs and data privacy issues poses an additional challenge. An approach such as meta-learning can help address this issue. This work showcases meta-learning with scarcely labeled data for the detection of multimodal fake news and provides a performance comparison of the meta-learning approach with the fully supervised learning approach. We leverage the power of Model-Agnostic Meta-Learning (MAml) and Fast Context Adaption via Meta-Learning (CAml) in this work. The results are encouraging as these meta-learning models achieve heightened accuracy and speed even with insufficient labeled data for multimodal fake news detection. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Meta-learning Assisted Graph Representation Learning for Downstream Learning Tasks 5th

Meta-learning Assisted Graph Representation Learning for Do...

引用

5th International Conference on Computing and Network Communications, CoCoNet 2023

作者： Bhat, Nischal R. Kulkarni, Prerana Sanjay Menon, Ananya Meda, Smruthika S. Das, Bhaskarjyoti Department of Computer Science and Engineering PES University Karnataka Bengaluru India Department of Computer Science and Engineering in AI & ML PES University Karnataka Bengaluru India

ISBN: (纸本)9789819747108

The Graph Transformer Network (GTN) is a state-of-the-art solution for graph representation learning, which utilizes the transformer architecture to capture attention and long-range dependencies in a non-euclidean dataset such as a graph. However, even with GTN in a downstream learning task, there are usually a few data points that are harder to classify than others and are at risk of being wrongly classified. Metric-based meta-learning, which encompasses many meta-learning algorithms, proves promising in such scenarios. Through this work, we propose a novel 2-stage pipeline combining a Graph Transformer Network with metric-based meta-learning methodologies to make downstream classification tasks easier. The work described in this article investigates and evaluates this pipeline in two specific learning setups using two Metric Learning frameworks, i.e., a Siamese Network for binary classification of graphs and a Prototypical Network for multi-class classification of nodes, both appended to a representation learning block of Graph Transformer Network. The experiments described in this article conclusively prove the efficacy of such a pipeline both in full-shot and few-shot learning scenarios. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Diffusion models for 3D generation: A survey

引用

Computational Visual Media 2025年第1期11卷 1-28页

作者： Chen Wang Hao-Yang Peng Ying-Tian Liu Jiatao Gu Shi-Min Hu Department of Computer and Information Science University of PennsylvaniaPhiladelphiaPennsylvania 19104USA Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China Machine Learning Research Apple AI/MLNew YorkUSA.E-mail:jiatao@***

Denoising diffusion models have demonstrated tremendous success in modeling data distributions and synthesizing high-quality *** the 2D image domain,they have become the state-of-the-art and are capable of generating photo-realistic images with high *** recently,researchers have begun to explore how to utilize diffusion models to generate 3D data,as doing so has more potential in real-world *** requires careful design choices in two key ways:identifying a suitable 3D representation and determining how to apply the diffusion *** this survey,we provide the first comprehensive review of diffusion models for manipulating 3D content,including 3D generation,reconstruction,and 3D-aware image *** classify existing methods into three major categories:2D space diffusion with pretrained models,2D space diffusion without pretrained models,and 3D space *** also summarize popular datasets used for 3D generation with diffusion *** with this survey,we maintain a repository https://***/cwchenwang/awesome-3d-diffusion to track the latest relevant papers and ***,we pose current challenges for diffusion models for 3D generation,and suggest future research directions.

关键词： diffusion models 3D generation generative models aiG

来源：评论

学校读者我要写书评

暂无评论

Deep Learning based air Quality Forecasting using Satellite Data 6

Deep Learning based Air Quality Forecasting using Satellite ...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Sree, K. Navya Reddy, Mancharla Rakesh Saraswathi, S. Department of Computer Science and Engineering Specialization with AI & ML Sathyabama Institute of Science and Technology Chennai India Department Computer science and engineering Sathyabama Institute of Science and Technology Chennai India

ISBN: (纸本)9798331522667

air pollution is a significant threat to human health and the environment. Accurate air quality forecasting is essential for effective mitigation strategies, including public health advisories, emission control measures, and policy interventions. This research focuses on the development of an advanced air quality forecasting system using machine learning techniques. The system uses historical data on pollutants such as PM2.5, NO2, and O3, along with meteorological parameters, to predict future air quality levels. The model is enhanced with the inclusion of sophisticated machine learning algorithms to better capture the intricate spatiotemporal patterns and enhance the accuracy of forecasting. The system may potentially provide real-time air quality forecasts that enable proactive measures for protecting public health and inform decisions for environmental policy. This research contributes to sustainable and resilient urban environments by providing valuable insights into air quality dynamics and supporting effective air pollution mitigation strategies. © 2025 IEEE.

关键词： air pollution air quality forecasts cardiovascular diseases data-driven strategies environmental policy global climate international collaboration machine learning NO2 O3 PM2.5 policy-making pollution mitigation proactive alerts public health real-time monitoring respiratory diseases spatial variability temporal variability transboundary pollution

来源：评论

学校读者我要写书评

暂无评论

Power synchronization: taming massive diversified serverless functions under power constraints

引用

science China(Information sciences) 2025年第3期68卷 47-65页

作者： Du LIU Lu ZHANG Yechen XU Xinkai WANG Lingyu SUN Yifei PU Xiaofeng HOU Chao LI Minyi GUO Department of Computer Science and Engineering Shanghai Jiao Tong University AI Chip Center for Emerging Smart Systems The Hong Kong University of Science and Technology

Carbon neutrality has become an important design objective worldwide. However, the on-going shift to cloud-naive era does not necessarily mean energy efficiency. From the perspective of power management, co-hosted serverless functions are difficult to tame. They are lightweight, short-lived applications sensitive to power capping activities. In addition, they exhibit great individual and temporal variability, presenting idiosyncratic performance/power scaling goals that are often at odds with one another. To date, very few proposals exist in terms of tailored power management for serverless platforms. In this work, we introduce power synchronization, a novel yet generic mechanism for managing serverless functions in a power-efficient way. Our insight with power synchronization is that uniform application power behavior enables consistent and uncompromised function operation on shared host machines. We also propose PowerSync, a synchronization-based power management framework that ensures optimal efficiency based on a clear understanding of functions. Our evaluation shows that PowerSync can improve the energy efficiency of functions by up to 16% without performance loss compared to conventional power management strategies.

关键词： serverless computing variability energy efficiency power management power synchronization

来源：评论

学校读者我要写书评

暂无评论

A survey on cross-user federated recommendation

引用

science China(Information sciences) 2025年第4期68卷 7-32页

作者： Enyue YANG Yudi XIONG Wei YUAN Weike PAN Qiang YANG Zhong MING College of Computer Science and Software Engineering Shenzhen University School of Electrical Engineering and Computer Science The University of Queensland WeBank AI Lab WeBank Department of Computer Science and Engineering Hong Kong University of Science and Technology College of Big Data and Internet Shenzhen Technology University Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)

Recommender systems are effective in mitigating information overload, yet the centralized storage of user data raises significant privacy concerns. Cross-user federated recommendation(CUFR) provides a promising distributed paradigm to address these concerns by enabling privacy-preserving recommendations directly on user devices. In this survey, we review and categorize current progress in CUFR, focusing on four key aspects: privacy, security, accuracy, and efficiency. Firstly,we conduct an in-depth privacy analysis, discuss various cases of privacy leakage, and then review recent methods for privacy protection. Secondly, we analyze security concerns and review recent methods for untargeted and targeted *** untargeted attack methods, we categorize them into data poisoning attack methods and parameter poisoning attack methods. For targeted attack methods, we categorize them into user-based methods and item-based methods. Thirdly,we provide an overview of the federated variants of some representative methods, and then review the recent methods for improving accuracy from two categories: data heterogeneity and high-order information. Fourthly, we review recent methods for improving training efficiency from two categories: client sampling and model compression. Finally, we conclude this survey and explore some potential future research topics in CUFR.

关键词： cross-user federated recommendation federated recommendation federated learning recommender systems user privacy

来源：评论

学校读者我要写书评

暂无评论

Twin attention based multi-task convolutional bidirectional long short term memory for facial expression recognition

引用

Multimedia Tools and Applications 2025年第10期84卷 8037-8070页

作者： Sreenivas, Velagapudi Sivaneasan, B. Vani, K. Suvarna Chakrabarti, Prasun Singapore Institute of Technology Singapore138683 Singapore Engineering Cluster Singapore Institute of Technology Singapore138683 Singapore Department of Computer Science and Engineering AI/ML Research Group Head VR Siddhartha Engineering College Andhra Pradesh Vijayawada520007 India Department of Computer Science and Engineering Sir Padampat Singhania University Rajasthan Udaipur313601 India

Facial Expression Recognition (FER) aims to detect the emotional state of facial images. It is playing an increasingly important role in several application areas, including human–computer interaction (HCI), video transcriptions, and social communications. This article provides an adequate attention-based multi-task deep learning method for facial expression recognition. First, the input videos are collected from the RAVDESS and MELD datasets. Then, the input videos are converted using a threshold-based keyframe extraction algorithm. Next, the input data is pre-processed using the Adaptive Pixel Density Median Filtering (A-PDMF) method. Key features such as shape, color and texture are extracted from the pre-processed images. Finally, the facial expressions are recognized by proposing a novel twin attention-based multi-task convolutional bidirectional long-short-term memory method (TA-MC-BiLSTM). In addition, the classification parameters are optimally tuned using the EX-AHA method (Extended Artificial Hummingbird Algorithm). The proposed model reduces the size of facial features while accurately identifying the wide range of facial expressions. For simulation, the proposed method prefers python tool and results are analyzed using RAVDESS and MELD datasets. The simulation results show that the proposed model provides better results than other existing models in terms of accuracy of 99.6% for RAVEDESS and 99.4% for MELD. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning-Based Fault Classification Methods for Solar Photovoltaic Modules: A Comparative Analysis 6th

Transfer Learning-Based Fault Classification Methods for Sol...

引用

6th International Conference on Intelligent Communication, Control and Devices, ICICCD 2024

作者： Supriya Shukla, Ashutosh Manchanda, Mahesh Department of AI and ML COER University Roorkee247667 India Electrical Cluster School of Engineering UPES Dehradun India Department of Computer Science and Engineering GEHU University Dehradun India

ISBN: (纸本)9789819783281

India’s reliance on fossil fuels to meet its energy generation demands has a negative impact on both the environment and public health. In the present energy transition, photovoltaic (PV) technologies have become more widely accepted for commercial use, achieved significant progress in technology, and have a major role to play in reducing the harmful environmental effects of fossil fuel-based power generation. Soiling research on solar PV has notably increased in recent years due to its critical role in reducing the performance of solar PV cells. Therefore, to guarantee the amount of power yield, efficient monitoring of the soiling is crucial. It is difficult to manually analyse soiling severity on the panel images due to the non-uniformity of the type and amount of soiling faults. Deep learning models have been successfully applied to the analysis of solar panel images and soiling categorization;nevertheless, this approach may require a significant amount of training time and may lead to gradient descent. To tackle these training issues, we propose a comparative study of two pre-trained neural network architectures, namely, MobileNetV3small and RestNet50, on a publicly available dataset of 875 images of six solar PV fault classes, namely, clean, dust, bird-drop, electrical damage, physical damage, and snow-covered. The experimental results show that MobileNetV3small achieved a better performance of 98%. The results show that MobileNetV3small obtained a promising result of 11% higher classification accuracy than ResNet50, with an accuracy of 86.6%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Electric losses

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：