检索结果-内蒙古大学图书馆

DSAF: A Dual-Stage Attention Based Multimodal Fusion Framework for Medical Visual Question Answering

SN computer science 2025年第4期6卷 1-16页

作者： Mukesh, K. Jayaprakash, S.L. Prasanna Kumar, R. Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Tamilnadu Chennai 601103 India

In the realm of clinical healthcare, medical visual question answering systems emerge as a pivotal innovation that plays a crucial role in clinical decision-making and patient care. They are designed to interpret medical images in response to free-form natural language questions, thereby facilitating a more nuanced and comprehensive understanding of patient diagnostics. This approach seeks to bridge the gap between complex medical imagery and the clinical questions they prompt, offering a novel avenue for enhancing diagnostic accuracy and efficiency. We introduce the Dual Stage Attention-based Fusion framework, which leverages an advanced feature fusion strategy, along with image encoding techniques and state-of-the-art biomedical language models, to process and analyze medical images and textual queries concurrently. By employing a dual-stage attention mechanism, the proposed model enhances feature extraction and integration, enabling a more accurate and refined analysis of both visual and textual data. The model specifically addresses the challenges commonly associated with medical visual question answering, including the intricate nature of medical imagery and the scarcity of high-quality, annotated medical datasets. The proposed multimodal augmentation technique, involving an autoencoder and generative language model, significantly enriches the data for model training which mitigates the data scarcity issue and enhances the model’s ability to generalize across different medical queries. Empirical validation of our model on the VQA-RAD and SLAKE datasets demonstrates its exceptional performance, achieving state-of-the-art accuracies of 80.8% and 86.2% respectively. These results underscore the model’s potential in AI-enhanced medical diagnostics and decision support systems to offer unprecedented diagnostic insights and patient care solutions. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Data fusion Dual-stage attention Multimodal learning Vision language model Visual reasoning

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral imagery quality assessment and band reconstruction using the prophet model

引用

CAAI Transactions on Intelligence Technology 2025年第1期10卷 47-61页

作者： Ping Ma Jinchang Ren Zhi Gao Yinhe Li Rongjun Chen National Subsea Centre School of ComputingEngineering and TechnologyRobert Gordon UniversityAberdeenUK School of Computer Science Guangdong Polytechnic Normal UniversityGuangzhouChina School of Remote Sensing and Information Engineering Wuhan UniversityWuhanChina

In Hyperspectral Imaging(HSI),the detrimental influence of noise and distortions on data quality is profound,which has severely affected the following-on analytics and decisionmaking such as land *** study presents an innovative framework for assessing HSI band quality and reconstructing the low-quality bands,based on the Prophet *** introducing a comprehensive quality metric to start,the authors approach factors in both spatial and spectral characteristics across local and global *** metric effectively captures the intricate noise and distortions inherent in the HSI ***,the authors employ the Prophet model to forecast information within the low-quality bands,leveraging insights from neighbouring high-quality *** validate the effectiveness of the authors’proposed model,extensive experiments on three publicly available uncorrected datasets are *** a head-to-head comparison,the framework against six state-ofthe-art band reconstruction algorithms including three spectral methods,two spatialspectral methods and one deep learning method is *** authors’experiments also delve into strategies for band selection based on quality metrics and the quality evaluation of the reconstructed *** addition,the authors assess the classification accuracy utilising these reconstructed *** various experiments,the results consistently affirm the efficacy of the authors’method in HSI quality assessment and band ***,the authors’approach obviates the need for manually prefiltering of noisy *** comprehensive framework holds promise in addressing HSI data quality concerns whilst enhancing the overall utility of HSI.

关键词： band reconstruction band quality hyperspectral image(HSI) prophet model

来源：评论

学校读者我要写书评

暂无评论

A survey on dynamic graph processing on GPUs: concepts, terminologies and systems

引用

Frontiers of computer science 2024年第4期18卷 1-23页

作者： Hongru GAO Xiaofei LIAO Zhiyuan SHAO Kexin LI Jiajie CHEN Hai JIN National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China Zhejiang Lab Hangzhou 311121China

Graphs that are used to model real-world entities with vertices and relationships among entities with edges,have proven to be a powerful tool for describing real-world problems in *** most real-world scenarios,entities and their relationships are subject to constant *** that record such changes are called dynamic *** recent years,the widespread application scenarios of dynamic graphs have stimulated extensive research on dynamic graph processing systems that continuously ingest graph updates and produce up-to-date graph analytics *** the scale of dynamic graphs becomes larger,higher performance requirements are demanded to dynamic graph processing *** the massive parallel processing power and high memory bandwidth,GPUs become mainstream vehicles to accelerate dynamic graph processing ***-based dynamic graph processing systems mainly address two challenges:maintaining the graph data when updates occur(i.e.,graph updating)and producing analytics results in time(i.e.,graph computing).In this paper,we survey GPU-based dynamic graph processing systems and review their methods on addressing both graph updating and graph *** comprehensively discuss existing dynamic graph processing systems on GPUs,we first introduce the terminologies of dynamic graph processing and then develop a taxonomy to describe the methods employed for graph updating and graph *** addition,we discuss the challenges and future research directions of dynamic graph processing on GPUs.

关键词： dynamic graphs graph processing graph algorithms GPUs

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Approach to Dynamic Thread Allocation Driven by Workload and Task Prioritization

引用

SN computer science 2025年第3期6卷 1-19页

作者： Abirami, K. Harini, N. Department of Computer Science and Engineering Amrita School of Computing Coimbatore Amrita Vishwa Vidyapeetham Coimbatore India

In today’s rapidly changing world, cloud service providers face numerous challenges in managing resources and meeting customer demands. To address these challenges, cloud service providers should prioritize the tasks and allocate threads efficiently. By allocating threads efficiently, service providers can optimize resource utilization and reduce response times and job completion times which in turn improves customer satisfaction. We propose a hybrid model that integrates the threshold-driven thread Balancer (TDTB) for dynamic thread allocation with a Customer Retention Model (CRM) to prioritize tasks based on customer behaviour. Our model initiates the establishment of a thread pool configured with a dynamic threshold based on workload (on-demand requests). Concurrently, a queue to handle incoming customer requests is set up alongside a CRM priority queue designed for task prioritization. Our model calculates Job duration and completion times for n priority classes. Crown consumers experience shorter durations and completion times compared to other priority classes. Tasks are completed in descending order of priority. The results of thorough experimentation clearly show that crown consumer tasks are highly satisfied. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Customer segmentation Response time Service differentiation Thread allocation Throughput Workload

来源：评论

学校读者我要写书评

暂无评论

An Improved Robust Sparse Convex Clustering

引用

Tsinghua science and Technology 2023年第6期28卷 989-998页

作者： Jinyao Ma Haibin Zhang Shanshan Yang Jiaojiao Jiang Gaidi Li Beijing Institute for Scientific and Engineering Computing Faculty of ScienceBeijing University of TechnologyBeijing 100124China School of Computer Science and Engineering University of New South WalesSydney 2052Australia

Convex clustering,turning clustering into a convex optimization problem,has drawn wide *** overcomes the shortcomings of traditional clustering methods such as K-means,Density-Based Spatial Clustring of Applications with Noise(DBSCAN)and hierarchical clustering that can easily fall into the local optimal ***,convex clustering is vulnerable to the occurrence of outlier features,as it uses the Frobenius norm to measure the distance between data points and their corresponding cluster centers and evaluate *** accurately identify outlier features,this paper decomposes data into a clustering structure component and a normalized component that captures outlier *** from existing convex clustering evaluating features with the exact measurement,the proposed model can overcome the vast difference in the magnitude of different features and the outlier features can be efficiently identified and *** solve the proposed model,we design an efficient algorithm and prove the global convergence of the *** on both synthetic datasets and UCI datasets demonstrate that the proposed method outperforms the compared approaches in convex clustering.

关键词： convex clustering outlier features block coordinate descent Newton’s method

来源：评论

学校读者我要写书评

暂无评论

Secure location-aware geocast routing in Internet of Vehicles

引用

Multimedia Tools and Applications 2025年第18期84卷 19669-19692页

作者： Kumar, Sunil Dohare, Upasana Kumar, Sushil Department of Computer Science and Information Technology Central University of Haryana Mahendragarh India School of Computing Science & Engineering Galgotias University Greater Noida India School of Computer and Systems Sciences Jawaharlal Nehru University New Delhi India

Efficient message dissemination in Vehicular Ad Hoc Networks (VANETs) relies on robust connectivity between neighboring vehicular nodes, yet it is often compromised by malicious intruders. While recent literature proposes various approaches to enhance geocasting performance, security considerations for connectivity are often overlooked. To address this gap, we propose the Secure Location-Aware Cache Agent based Geocast Routing (SL-CAGR) protocol, emphasizing an Intrusion Prevention Technique (IPT) for message integrity preservation and a Connectivity Reliant Packet Forwarding (CRPF) algorithm for improved VANET connectivity. Our protocol introduces a network model for cache agent-based geocast routing on the Internet of Vehicle (IoV) environment, implements IPT using Diffie-Hellman digital signatures, and presents a secure geocast routing strategy focusing on re-caching and cache agent selection. Empirical simulations demonstrate SL-CAGR's superiority in packet delivery ratio, packet loss, duplication, hop count, end-to-end delay, and network load compared to these protocols. Simulation results demonstrate that SL-CAGR outperforms state-of-the-art techniques like CAG, CTRC, and D-Flooding. SL-CAGR stands out by merging intrusion prevention, secure geocast routing, and cache agent selection, ensuring robust security and efficiency in VANETs. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Agri-Ontology: A Novel Ontology Framework for Agricultural Domain 3

Agri-Ontology: A Novel Ontology Framework for Agricultural D...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Deepa, R. Jayaraman, Venkatesh Srinivasulu, Senduru Umamageswari, B. Surendran, R. Srm Institute of Science & Technology School of Computing Department of Computing Technologies Kattankulathur Tamilnadu Chennai603203 India Chennai Institute of Technology Department of Computer Science and Engineering Chennai600069 India Sathyabama Institute of Science and Technology School of Computing Department of Computer Science and Engineering Chennai600119 India Srm Institute of Science & Technology School of Computing Department of Computing Technologies Chennai600119 India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331509675

The agricultural information system deals with massive amounts of data from heterogeneous sources. It helps the farmers gain accurate information by providing better insights. A significant issue in agricultural data is its unstructured form, which can be resolved through ontology - a novel framework known as AgriOntology is proposed to address this issue for the Agrovoc dataset. The data in the unstructured form is initially pre-processed through the Natural Language Processing approach to generate features for ontology construction. The BERT and Jaccard similarity are applied to establish a relationship between the features used to construct the Agri-Ontology. Post ontology construction, the BiGAN framework is used to analyze the performance. The performance of the constructed ontology is observed to have an accuracy of 94.64%, which is higher than the existing models. © 2025 IEEE.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Time Series Segmentation Network Based on Eddy Current Testing for Detecting Surface Metal Defects

引用

IEEE/CAA Journal of Automatica Sinica 2025年第3期12卷 528-538页

作者： Xiaorui Li Xiaojuan Ban Haoran Qiao Zhaolin Yuan Hong-Ning Dai Chao Yao Yu Guo Mohammad S.Obaidat George Q.Huang the School of Intelligence Science and Technology University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering the Key Laboratory of Intelligent Bionic Unmanned Systems and the Institute of Materials Intelligent Technology Liaoning Academy of Materials IEEE the Department of Computer Science Hong Kong Baptist University the School of Computer and Communication Engineering Key Laboratory of Advanced Materials and Devices for Post-Moore Chips Ministry of Education University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering University of Science and Technology Beijing the School of Computer and Communication Engineering University of Science and Technology Beijing the King Abdullah Ⅱ School of Information Technology The University of Jordan the Department of Computational Intelligence the School of Computing SRM University the School of Engineering The Amity University The Hong Kong Polytechnic University

In high-risk industrial environments like nuclear power plants, precise defect identification and localization are essential for maintaining production stability and safety. However, the complexity of such a harsh environment leads to significant variations in the shape and size of the defects. To address this challenge, we propose the multivariate time series segmentation network(MSSN), which adopts a multiscale convolutional network with multi-stage and depth-separable convolutions for efficient feature extraction through variable-length templates. To tackle the classification difficulty caused by structural signal variance, MSSN employs logarithmic normalization to adjust instance distributions. Furthermore, it integrates classification with smoothing loss functions to accurately identify defect segments amid similar structural and defect signal subsequences. Our algorithm evaluated on both the Mackey-Glass dataset and industrial dataset achieves over 95% localization and demonstrates the capture capability on the synthetic dataset. In a nuclear plant's heat transfer tube dataset, it captures 90% of defect instances with75% middle localization F1 score.

关键词： Eddy current testing nondestructive testing semantic segmentation time series analysis

来源：评论

学校读者我要写书评

暂无评论

Hyper-personalized employment in urban hubs: multimodal fusion architectures for personality-based job matching

引用

Neural computing and Applications 2024年 1-16页

作者： Jain, Dipika Sangwan, Saurabh Raj Kumar, Akshi Department of Computer Science and Engineering Delhi Technological University New Delhi India School of Computer Science and Engineering Galgotias University Greater Noida India Department of Computing Goldsmiths University of London London United Kingdom

In the evolving landscape of smart cities, employment strategies have been steering towards a more personalized approach, aiming to enhance job satisfaction and boost economic efficiency. This paper explores an advanced solution by integrating multimodal deep learning to create a hyper-personalized job matching system based on individual personality traits. We employed the First Impressions V2 dataset, a comprehensive collection encompassing various data modalities suitable for extracting personality insights. Among various architectures tested, the fusion of XceptionResNet with BERT emerged as the most promising, delivering unparalleled results. The combined model achieved an accuracy of 92.12%, an R2 score of 54.49%, a mean squared error of 0.0098, and a root mean squared error of 0.0992. These empirical findings demonstrate the effectiveness of the XceptionResNet + BERT in mapping personality traits, paving the way for an innovative, and efficient approach to job matching in urban environments. This work has the potential to revolutionize recruitment strategies in smart cities, ensuring placements that are not only skill-aligned but also personality-congruent, optimizing both individual satisfaction and organizational productivity. A set of theoretical case studies in technology, banking, healthcare, and retail sectors within smart cities illustrate how the model could optimize both individual satisfaction and organizational productivity. © The Author(s) 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Smart Compiler Assistant: An AST based Python Code Analysis 15

Smart Compiler Assistant: An AST based Python Code Analysis

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Aneesh, C.H. Saumik, Gembali Varun, K.V.V. Belwal, Meena Amrita School of Computing Artificial Inteligence Engineering Bengaluru India Amrita School of Computing Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350370249

There are many challenges when it comes to compiling huge lines of code or codes with huge time complexity. Also, if there is an error in the last line of the code, for example, a simple syntax error or a syntactic error, all the time for compiling the code is wasted. To reduce the time and to compile an error-free code, The novel 'Smart Compiler Assistant', a tool is designed to revolutionize the coding experience for developers by learning the words and structure of code. The 'smart compile assistant' offers guidance in the optimization, completion, and correction of code, that in turn, improves productivity and the quality of the code. Equipped with smooth interoperability into commonly used development tools, 'Smart Compiler Assistant', lets developers produce cleaner, more efficient codes with greater accuracy and less hassle, boosting the overall efficiency of the software development cycle. © 2024 IEEE.

关键词： Coding errors

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：