检索结果-内蒙古大学图书馆

31st International Conference on Computational Linguistics, COLING 2025

作者： Zafar, Aizan Mishra, Kshitij Ekbal, Asif Department of Computer Science and Engineering Indian Institute of Technology Patna India School of AI and Data Science Indian Institute of Technology Jodhpur India

ISBN: (纸本)9798891761964

In medical question-answering, traditional knowledge triples often fail due to superfluous data and their inability to capture complex relationships between symptoms and treatments across diseases. This limits models' ability to provide accurate, contextually relevant responses. To overcome this, we introduce MedEx, which employs First-Order Logic (FOL)-based reasoning to model intricate relationships between diseases and treatments. We construct FOL-based triplets that encode the interplay of symptoms, diseases, and treatments, capturing not only surface-level data but also the logical constraints of the medical domain. MedEx encodes the discourse (questions and context) using a transformer-based unit, enhancing context comprehension. These encodings are processed by a Knowledge Injection Cell that integrates knowledge graph triples via a Graph Attention Network. The Logic Fusion Cell then combines medical-specific logical rule triples (e.g., co-occurrence, causation, diagnosis) with knowledge triples and extracts answers through a feed-forward layer. Our analysis demonstrates MedEx's effectiveness and generalization across medical question-answering tasks. By merging logical reasoning with knowledge, MedEx provides precise medical answers and adapts its logical rules based on training data nuances. © 2025 Association for Computational Linguistics.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Neuroimaging Precision: Crafting a Stacked VGG19-Logistic Fusion for Breakthrough Early Detection of Alzheimer's 9

Neuroimaging Precision: Crafting a Stacked VGG19-Logistic Fu...

引用

9th International Conference on Science, Technology, engineering and Mathematics, ICONSTEM 2024

作者： Selvi, G. Anbu Karthick, T. Srmist Department of Computer Science And Engineering Chennai Kattankulathur India School of Computing Srmist Department of Data Science And Business Systems Chennai Kattankulathur India

ISBN: (纸本)9798350365092

Several medical investigations have demonstrated that Alzheimer's disease (AD) manifests itself long before the formal diagnosis of dementia. These studies have led to the identification of numerous ideal biomarkers associated with Alzheimer's symptoms. Consequently, the imperative for early diagnosis has become evident, necessitating a high-performance computational tool capable of efficiently processing vast amounts of data. Early detection of AD not only offers valuable insights into the condition's progression but also presents a significant opportunity to benefit from timely and effective treatment. This ground-breaking study pioneers an innovative approach to the early detection and diagnosis of AD by crafting a sophisticated model SVGGL, which blends the power of stacked VGG19 neural networks with the interpretability of logistic regression. Leveraging neuro-imaging data, specifically the insights provided MRI, and our model aims to discern subtle structural and functional alterations in the brains of individuals at risk for or in the early stages of AD. The combination of feature extraction from stacked VGG19 models and subsequent logistic regression classification yields a precise and efficient classifier with an outstanding accuracy of 98.24%. With such a high degree of accuracy, the model can reliably differentiate among healthy people and those with Alzheimer's, opening the door to potential early intervention and individualized treatment plans. The study not only sheds light on the intricate neuro pathological landscape of AD but also propels us toward a future where cutting-edge technology and data-driven insights, exemplified by our high-accuracy model, converge to tackle the challenges posed by this prevalent neurodegenerative disorder. © 2024 IEEE.

关键词： Neuroimaging

来源：评论

学校读者我要写书评

暂无评论

Classification of hyperspectral images using fusion of CNN and MiniGCN with SVM

引用

International Journal of Digital Earth 2023年第1期16卷 3601-3617页

作者： Wenbing Wu Tariq Sadad Mejdl Safran Sultan Alfarhood Xiaojian Yuan Big Data College Fuzhou University of International Studies and TradeFuZhouPeople’s Republic of China Department of Computer Science University of Engineering&TechnologyMardanPakistan Department of Computer Science College of Computer and Information SciencesKing Saud UniversityP.O.Box 51178Riyadh11543Saudi Arabia

Convolutional neural networks(CNNs)have gained popularity for categorizing hyperspectral(HS)images due to their ability to capture representations of spatial-spectral ***,their ability to model relationships between data is *** convolutional networks(GCNs)have been introduced as an alternative,as they are effective in representing and analyzing irregular data beyond grid *** have *** computationally intensive,minibatch GCNs(miniGCNs)enable minibatch training of large-scale *** have improved the classification performance by using miniGCNs to infer out-of-sample data without retraining the *** addition,fuzing the capabilities of CNNs and GCNs,through concatenative fusion has been shown to improve performance compared to using CNNs or GCNs ***,support vector machine(SvM)is employed instead of softmax in the classification *** techniques were tested on two HS datasets and achieved an average accuracy of 92.80 using Indian Pines dataset,demonstrating the effectiveness of miniGCNs and fusion strategies.

关键词： CNN hyperspectral images MiniGCN SVM

来源：评论

学校读者我要写书评

暂无评论

Automatic classification of normal/AD brain MRI slices using whale-algorithm optimized hybrid image features

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第10期14卷 14237-14248页

作者： Kadry, Seifedine Jessy, V. Elizabeth Rajinikanth, Venkatesan Crespo, Rubén González Department of Applied Data Science Noroff University College Kristiansand4612 Norway College of Engineering and Information Technology Ajman University Ajman United Arab Emirates Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon Division of Research and Innovation Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Tamil Nadu Chennai602105 India Department of Computer Science and Technology Universidad Internacional de La Rioja La Rioja Logroño Spain

In recent years, the prevalence of Age-Related Illnesses (ARL) has been increasing among older individuals, and early recognition and treatment will result in better living conditions. It is well known that Alzheimer's Disease (AD) is among the ARD, and severe cases may result in dementia as well. It is the purpose of this study to propose a technique for distinguishing normal/AD brain MRI slices with improved accuracy utilizing the T2-modality. This scheme consists following phases: (i) Brain MRI collection and preprocessing, (ii) Deep feature extraction with the chosen scheme, (iii) Handcrafted feature extraction, (iv) Whale Algorithm (WA) based feature reduction and serial integration, and (v) binary classification using five-fold cross-validation. A total of 2000 MRI slices (1000 normal and 1000 AD class) are examined during this task using images collected from Alzheimer’s Disease Neuroimaging Initiative (ADNI). This study confirms that the proposed scheme provides a classification accuracy of > 98% when applied with the K-Nearest Classifier. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence-Enabled Cooperative Cluster-Based data Collection for Unmanned Aerial Vehicles

引用

computers, Materials & Continua 2022年第11期73卷 3351-3365页

作者： R.Rajender C.S.S.Anupama G.Jose Moses E.Laxmi Lydia Seifedine Kadry Sangsoon Lim Department of Computer Science Engineering Lendi Institute of Engineering&TechnologyDenkada535005India Department of Electronics&Instrumentation Engineering V.R.Siddhartha Engineering CollegeVijayawada520007India Department of Computer Science Engineering Malla Reddy Engineering College500100India Department of Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India Department of Applied Data Science Noroff University CollegeKristiansand4612Norway Department of Computer Engineering Sungkyul UniversityAnyang14097Korea

In recent times,sixth generation(6G)communication technologies have become a hot research topic because of maximum throughput and low delay services for mobile *** encompasses several heterogeneous resource and communication standard in ensuring incessant availability of *** the same time,the development of 6G enables the Unmanned Aerial Vehicles(UAVs)in offering cost and time-efficient solution to several applications like healthcare,surveillance,disaster management,*** UAV networks,energy efficiency and data collection are considered the major process for high quality network *** these procedures are found to be challenging because of maximum mobility,unstable links,dynamic topology,and energy restricted *** issues are solved by the use of artificial intelligence(AI)and energy efficient clustering techniques for UAVs in the 6G *** this inspiration,this work designs an artificial intelligence enabled cooperative cluster-based data collection technique for unmanned aerial vehicles(AECCDC-UAV)in 6G *** proposed AECCDC-UAV technique purposes for dividing the UAV network as to different clusters and allocate a cluster head(CH)to each cluster in such a way that the energy consumption(ECM)gets *** presented AECCDC-UAV technique involves a quasi-oppositional shuffled shepherd optimization(QOSSO)algorithm for selecting the CHs and construct *** QOSSO algorithm derives a fitness function involving three input parameters residual energy of UAVs,distance to neighboring UAVs,and degree of *** performance of the AECCDC-UAV technique is validated in many aspects and the obtained experimental values demonstration promising results over the recent state of art methods.

关键词： 6G unmanned aerial vehicles resource allocation energy efficiency artificial intelligence clustering data collection

来源：评论

学校读者我要写书评

暂无评论

From Efficiency to Innovation: LLM 5.0 and the Future of Industry

From Efficiency to Innovation: LLM 5.0 and the Future of Ind...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Gantayat, Pradosh Kumar Kaur, Tejinder Majhi, Madhusmita Jena, Uttam Kumar Das, Swatismita Soni Department of Artificial Intelligence and Data Science Telangana Hyderabad501203 India Department of Mmictbm Mullana Haryana Ambala133207 India Department of Computer Science and Engineering Telangana Hyderabad501203 India Raajdhani Engineering College Biju Patnaik University of Technology Department of Computer Science and Engineering Odisha Bhubaneswar India Raajdhani Engineering College Bhubaneswar India

ISBN: (纸本)9798331509828

Industry 5.0 is a new way of thinking that is consistent with the ideas of Industry 4.0 but places greater emphasis on sustainability, sustainability, and human-centricity. Unlike Industry 4.0, which emphasizes the efficient integration of advanced technologies such as the Internet, AI, robots, and automation, Industry 5.0 seeks to balance human-machine collaboration to create more inclusive, meaningful, and sustainable systems. In Industry 5.0, LLM has a bigger role than automating similar activities. LLMs make sectors more resilient, adaptable and aligned with social values by fostering innovation, improving human-centred processes and promoting sustainable practices. Industry 5.0 will create a revolutionary force in the global industrial landscape thanks to a combination of emerging technologies that will further enhance the synergies between human creativity and machine intelligence. © 2025 IEEE.

关键词： Human-AI Collaboration Industrial Efficiency Industry 5.0 Innovation LLM 5.0

来源：评论

学校读者我要写书评

暂无评论

Knowledge Graphs Can be Learned with Just Intersection Features 41

Knowledge Graphs Can be Learned with Just Intersection Featu...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Le, Duy Zhong, Shaochen Liu, Zirui Xu, Shuai Chaudhary, Vipin Zhou, Kaixiong Xu, Zhaozhuo Department of Computer and Data Sciences Case Western Reserve University United States Department of Computer Science Rice University United States Department of Electrical and Computer Engineering North Carolina State University United States Department of Computer Science Stevens Institute of Technology United States

Knowledge Graphs (KGs) are potent frameworks for knowledge representation and reasoning. Nevertheless, KGs are inherently incomplete, leaving numerous uncharted relationships and facts awaiting discovery. Deep learning methodologies have proven effective in enhancing KG completion by framing it as a link prediction task, where the goal is to discern the validity of a triple comprising a head, relation, and tail. The significance of structural information in assessing the validity of a triple within a KG is well-established. However, quantifying this structural information poses a challenge. We need to pinpoint the metric that encapsulates the structural information of a triple and smoothly incorporate this metric into the link prediction learning process. In this study, we recognize the critical importance of the intersection among the k-hop neighborhoods of the head, relation, and tail when determining the validity of a triple. To address this, we introduce a novel randomized algorithm designed to efficiently generate intersection features for candidate triples. Our experimental results demonstrate that a straightforward fully-connected network leveraging these intersection features can surpass the performance of established KG embedding models and even outperform graph neural network baselines. Additionally, we highlight the substantial training time efficiency gains achieved by our network trained on intersection features. Copyright 2024 by the author(s)

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Assistive analytics for coronavirus-trends, patterns and predictions

Assistive analytics for coronavirus-trends, patterns and pre...

引用

International Conference on Artificial Intelligence, Blockchain, Computing and Security, ICABCS 2023

作者： Julian, Anitha Selvi, S. Kumaravel, Shyam Sundhar Veerasekaran, Sabarijeyanth Sajja, Sumanth Sai Department of Computer Science and Engineering Saveetha Engineering College Chennai India Department of Computer Science and Engineering R.M.K Engineering College Data Engineering Associate Accenture Chennai India Infosys Chennai India EGG S&S SW TCS Chennai India

ISBN: (纸本)9781032669663

The recently identified coronavirus is the source of the contagious sickness known as Covid-19. Most of the Covid-19 patients develop respiratory disorders that are recoverable since the infection is mild or moderate. But as the coronavirus has been thriving over the past three years uncontrollably, it has created new varied mutants, which has increased the fatality rate drastically and made it hard to be diagnosed on time. The proposed work suggests the analyzing of patient X-Ray as a more accurate step than the traditional swab test, in detecting the presence of the coronavirus through a mobile application. The infected person can get needed help on medication, treatment, hospitalization, etc. through the application. The application also marks the location of the Covid-19 infected persons using the geo-fencing visible to the other users in the same location that helps in avoiding contact with the infected. © 2024, CRC Press/Balkema. All rights reserved.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Paths to Systematically Unlocking the Frequency-Selective Potential of 3D Meta-Atoms 6

Evolutionary Paths to Systematically Unlocking the Frequency...

引用

6th Australian Microwave Symposium, AMS 2025

作者： Lv, Xiaojing Luo, Zhen Tyo, J. Scott Yang, Yang University of Technology School of Electrical and Data Engineering Sydney Australia University of Technology School of Mechanical and Mechatronic Engineering Sydney Australia Monash University Department of Electrical and Computer Systems Engineering Australia

ISBN: (纸本)9798350379969

This paper highlights the benefits of advanced multi-material 3D printing technology in enhancing the electromagnetic performance of metasurfaces. By systematically evolving geometric structures, the proposed bandpass filtering meta-Atom outperforms existing designs in key metrics, including bandwidth, out-of-band suppression, in-band insertion loss, and transition band steepness, underscoring the significant potential of 3D unit cells. Through the integration of qualitative approach and semi-Analytical design algorithm, the geometric topology is fully optimized without imposing substantial computational demands. © 2025 IEEE.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

A Novel CAD Framework with Visual and Textual Interpretability: Multimodal Insights for Predicting Respiratory Diseases 8

A Novel CAD Framework with Visual and Textual Interpretabili...

引用

8th International Artificial Intelligence and data Processing Symposium, IDAP 2024

作者： Mukhlis, Raza Saleem, Saied Kwon, Hyunwook Hussain, Jamil Aydin, Ahmet Arif Al-Antari, Mugahed A. Sejong University College of Ai Convergence Department of Artificial Intelligence and Data Science Seoul05006 Korea Republic of Inonu University Faculty of Engineering Department of Computer Engineering Malatya Turkey

ISBN: (纸本)9798331531492

Generating textual interpretability using recent advancements in large language models (LLMs) is crucial for enhancing the efficiency of comprehensive computer-aided diagnosis (CAD) systems. This improves transparency between medical staff, intelligent CAD systems, and end-users by creating a trustworthy and effective intermediate medical diagnosis environment. In this paper, an innovative explainable throughout CAD system is introduced, designed to predict diseases from Chest X-rays (CXR) in a comprehensive scenario. The primary goal is to undertake multiple tasks that reduce the burden on medical staff and enrich CAD outcomes, including classification, visual explanations (heatmaps), and textual report generation. The proposed CAD system is developed through eight key steps: data Collection and Annotation, data Preparation, Text Vectorizations (Indexing), Visual Encoder, RAG-Fusion, Structural Prompt, XAI LLmTextual Reasoning (LLM Model), and Final Output (LLM textual report, image classification, and heatmap localization). The AI-based CAD system is trained and evaluated using the public benchmark MIMIC-CXR dataset with 14 different classes. The classification performance achieved an overall accuracy of 70 %, precision of 70 %, and F1-score of 0.60 %, while for text report generation, the system obtained an average BERTScore precision of 0.83, RougeL 0.16, and a Meteor score of 0.28. These promising results suggest the potential for further improvement of the CAD system and its applicability to real-world medical tasks. © 2024 IEEE.

关键词： Diagnosis

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：