检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Didwania, Krish Seth, Pratinav Kasliwal, Aditya Agarwal, Amit Manipal Institute of Technology Manipal Academy of Higher Education Manipal India Department of Computer Science and Engineering India Department of Data Science & Computer Applications India Enterprise Analytics & Data Science Artificial Intelligence - Center of Excellence Wells Fargo International Solutions Private Limited Bangalore India

Agriculture, vital for global sustenance, necessitates innovative solutions due to a lack of organized domain experts, particularly in developing countries where many farmers are impoverished and cannot afford expert consulting. Initiatives like Farmers Helpline play a crucial role in such countries, yet challenges such as high operational costs persist. Automating query resolution can alleviate the burden on traditional call centers, providing farmers with immediate and contextually relevant information. The integration of Agriculture and Artificial Intelligence (AI) offers a transformative opportunity to empower farmers and bridge information gaps. Language models like transformers, the rising stars of AI, possess remarkable language understanding capabilities, making them ideal for addressing information gaps in agriculture. This work 1 explores and demonstrates the transformative potential of Large Language Models (LLMs) in automating query resolution for agricultural farmers, leveraging their expertise in deciphering natural language and understanding context. Using a subset of a vast dataset of real-world farmer queries collected in India, our study focuses on approximately 4 million queries from the state of Tamil Nadu, spanning various sectors, seasonal crops, and query types. Copyright © 2024, The Authors. All rights reserved.

关键词： Agriculture

来源：评论

学校读者我要写书评

暂无评论

Two-Dimensional MXenes:Innovative Materials for Efficient Thermal Management and Safety Solutions

引用

research 2024年第4期2024卷 80-100页

作者： XiaoYan Hu Qi Fan Shengchao Wang Yanxin Chen Degao Wang Ke Chen Fangfang Ge Wenhu Zhou Kun Liang School of Materials Science and Chemical Engineering Ningbo UniversityNingboZhejiang 315211P.R.China Zhejiang Key Laboratory of Data-Driven High-Safety Energy Materials and Applications Ningbo Key Laboratory of Special Energy Materials and ChemistryNingbo Institute of Materials Technology and EngineeringChinese Academy of SciencesNingbo 35201P.R.China University of Chinese Academy of Sciences Beijing 100049P.R.China Advanced Interdisciplinary Sciences Research(AIR)Center Ningbo Institute of Materials Technology and EngineeringChinese Academy of SciencesNingbo 315201P.R.China Qianwan Institute of CNITECH Ningbo 315336P.R.China Xiangya School of Pharmaceutical Sciences Central South UniversityChangsha 410013P.R.China

MXenes,a class of 2-dimensional transition metal carbides and nitrides,have garnered important attention due to their remarkable electrical and thermal conductivity,high photothermal conversion efficiency,and *** review explores the potential of MXene materials in various thermal applications,including thermal energy storage,heat dissipation in electronic devices,and the mitigation of electromagnetic interference in wearable *** advancements in MXene composites,such as MXene/bacterial cellulose aerogel films and MXene/polymer composites,have demonstrated enhanced performance in phase change thermal storage and electromagnetic interference shielding,underscoring their versatility and *** notable progress has been made,challenges remain,including the need for a deeper understanding of photothermal conversion mechanisms,improvements in mechanical properties,exploration of diverse MXene types,and the development of sustainable synthesis *** paper discusses these aspects and outlines future research directions,emphasizing the growing importance of MXenes in addressing energy efficiency,health,and safety concerns in modern applications.

关键词： MXene composites wear

来源：评论

学校读者我要写书评

暂无评论

Logic-Aware Knowledge Graph Reasoning for Structural Sparsity under Large Language Model Supervision 25

Logic-Aware Knowledge Graph Reasoning for Structural Sparsit...

引用

34th ACM Web Conference, WWW 2025

作者： Pan, Yudai Hong, Jiajie Zhao, Tianzhe Song, Lingyun Liu, Jun Shang, Xuequn School of Computer Science Northwest Polytechnical University Shaanxi Xi’an China Key Laboratory of Big Data Storage and Management Northwestern Polytechnical University Shaanxi Xi’an China School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an China Research & Development Institute of Northwestern Polytechnical University in Shenzhen Shenzhen China National Engineering Lab for Big Data Analytics Xi’an Jiaotong University Shaanxi Xi’an China

ISBN: (纸本)9798400712746

Knowledge Graph (KG) reasoning aims to predict missing entities in incomplete triples, which requires adequate structural information to derive accurate embeddings. However, KGs in the real world are not as dense as the idealized benchmarks, where sparse graph structures restrict the comprehensive structural information for superior performance. Although the logical semantics in KGs shows its potential in alleviating the impact of structural sparsity, there still exist some challenges. The deficient supervision and the semantic gap of logic make it difficult to introduce logical semantics in sparse KG reasoning. To this end, we propose a novel KG reasoning approach LoLLM injecting logic with the supervised information supplied by the Large Language Model (LLM), which is proved to be effective in evaluating and scoring. Firstly, LoLLM derives structural embeddings employing a graph convolutional network (GCN) with relation-aware and triple-aware attention. LoLLM secondly constructs reasoning paths instantiated from the first-order logic rules extracted from sparse KGs, and injects the logical semantics by a designed LLM-enhanced tuning strategy. We propose a textual loss (TL) and a logical loss (LL) in the optimization and obtain logical tuning embeddings of KG in this process. Finally, LoLLM fuses structural embeddings from the GCN and logical tuning embeddings from the LLM-enhanced tuning for scoring and incomplete triple prediction. Extensive experiments on two sparse KGs and a benchmark show that LoLLM outperforms state-of-the-art structure-based and Language Model (LM)-augmented baselines. Moreover, the logic rules with corresponding confidences provide explicit explanations as an interpretable paradigm. © 2025 Copyright held by the owner/author(s).

关键词： Structural analysis

来源：评论

学校读者我要写书评

暂无评论

NC-ALG: Graph-Based Active Learning Under Noisy Crowd

NC-ALG: Graph-Based Active Learning Under Noisy Crowd

引用

International Conference on data Engineering

作者： Wentao Zhang Yexin Wang Zhenbang You Yang Li Gang Cao Zhi Yang Bin Cui Center for Machine Learning Research Peking University Institute of Advanced Algorithms Research Shanghai National Engineering Labratory for Big Data Analytics and Applications Key Lab of High Confidence Software Technologies Peking University Department of Data Platform TEG Tencent Inc. Beijing Academy of Artificial Intelligence Institute of Computational Social Science Peking University Qingdao

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Graph Neural Networks (GNNs) have achieved great success in various data mining tasks but they heavily rely on a large number of annotated nodes, requiring considerable human efforts. Despite the effectiveness of existing GNN-based Active Learning (AL) methods, they assume that the annotated labels are always correct, which is contradictory to the error-prone labeling process in a practical crowdsourcing environment. Besides, due to this impractical assumption, existing works only focus on optimizing the node selection in AL but neglect optimizing the labeling process. Therefore, we present NC-ALG, the first GNN-based AL framework that optimizes both the node selection and node labeling process under a noisy crowd. For node selection, NC-ALG introduces a new measurement to model influence reliability and an effective influence maximization objective to select nodes. For node labeling, NC-ALG significantly reduces the labeling cost by considering the model-predicted labels and the labels of mirror nodes. To the best of our knowledge, this is the first attempt to consider GNN-based AL under the practical noisy crowd. Empirical studies on public datasets demonstrate that NC-ALG significantly outperforms existing methods in terms labeling efficiency. Notably, it only takes NC-ALG one-third of the labeling budget that the competitive baseline GRAIN needs to achieve an accuracy of 70.7 % on PubMed.

关键词： Crowdsourcing Costs Noise Predictive models Graph neural networks Labeling Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Character Classification and Actor Recognition in Yakshagana Images Using Machine Learning Techniques and Facial Makeup Pattern Analysis

Character Classification and Actor Recognition in Yakshagana...

引用

IEEE Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)

作者： Anantha Murthy Prathwini Sanjeev Kulkarni Savitha G Department of Master of Computer Applications NMAM Institute of Technology NITTE (Deemed to be University) Nitte Karkala and and Research Scholar Institute of Computer Science and Information Science” Srinivas University India Department of Master of Computer Applications NMAM Institute of Technology NITTE (Deemed to be University) Nitte Karkala India Department of Computer Science and Engineering Srinivas University Institute of Engineering and Technology Mangalore India Department of Data Science and Computer Applications Manipal Academy of higher Education Manipal Institute of Technology Manipal

ISBN: (数字)9798350350593

ISBN: (纸本)9798350350609

Yakshagana, a traditional theater form from Karnataka, India, features a unique combination of vibrant costumes, dynamic dance movements, and elaborate facial makeup, making character and actor identification a challenging task for automated systems. This research work presents a novel approach to classify Yakshagana characters into two primary categories, Vaishnava and Shaiva, and to identify the actors performing these characters using advanced machine learning techniques. Our research employs a Cyclic Gated Recurrent Neural Network (Cyclic GRNN) for classification and identification tasks. For character category classification, we integrate YOLOv3 and Faster R-CNN models, achieving an accuracy of 92.85% with YOLOv3 and 88.285% with Faster R-CNN. The categorization is specifically focused on distinguishing between Vaishnava and Shaiva characters. Additionally, for actor name identification, we utilize a RESNET-50 model, attaining a high accuracy of 95.60%. The results demonstrate the efficacy of Cyclic GRNN combined with state-of-the-art object detection and image classification models in accurately recognizing and categorizing Yakshagana characters and actors. This research contributes to the preservation and digital documentation of Yakshagana by providing robust tools for automated identification, thereby facilitating cultural heritage studies and enhancing audience engagement with this traditional art form.

关键词： YOLO Accuracy Image recognition Recurrent neural networks Machine learning Documentation Logic gates Character recognition Cultural differences Image classification

来源：评论

学校读者我要写书评

暂无评论

Integrating Artificial Intelligence and Multiple Intelligences for Advanced Educational Models

Integrating Artificial Intelligence and Multiple Intelligenc...

引用

2024 International Conference on Electrical, Electronics and Computing Technologies, ICEECT 2024

作者： Palarimath, Suresh Maran, Pyingkodi Venkateswaran, R. Wilfred Blessing, N.R. Shiny, K.V. Renuga, S. University of Technology and Applied Sciences College of Computing and Information Sciences Salalah Oman Kongu Engineering College Department of Computer Applications Erode India University of Technology and Applied Sciences College of Computing and Information Sciences Ibri Oman Bharath Institute of Higher Education and Research Department of Computer Science and Engineering Chennai India Panimalar Engineering College Department of Artificial Intelligence and Data Science Chennai India

ISBN: (纸本)9798350378092

The aim of educational innovation is to foster students' creative and problem-solving skills via the integration of several disciplines, including science, technology, engineering, art, and mathematics. Efficiently identifying and fostering the various abilities of pupils continues to be a crucial obstacle. This research presents a sophisticated educational approach that combines the notion of multiple intelligences with artificial intelligence (AI) technology to tackle this problem. This concept improves the teaching environment by including intelligent auxiliary services for instructors and students via the use of smart speech and picture interaction. Artificial intelligence (AI) integrated into the multiple intelligence's framework enables the ability to observe, analyze, and implement personalized teaching tactics in real-time using machine learning. The suggested AI-assisted education paradigm aims to enhance teacher-student interactions and facilitate personalized instruction. The study provides evidence that this technique successfully facilitates personalized and captivating learning experiences, promoting students' diverse talents and augmenting their creativity and problem-solving capabilities. This approach seeks to fundamentally transform conventional educational techniques by addressing the disparity between existing educational practices and the future requirements of the workforce. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Empowering Breast Cancer Detection with AI: A Modified Support Vector Machine Approach for Improved Classification Accuracy 4

Empowering Breast Cancer Detection with AI: A Modified Suppo...

引用

4th International Conference on Expert Clouds and applications, ICOECA 2024

作者： Palarimath, Suresh Maran, Pyingkodi Thenmozhi, K. Shiny, K.V. Sujatha, T. N.r, Wilfred Blessing College of Computing and Information Sciences University of Technology and Applied Information Technology Department Sciences Salalah Oman Kongu Engineering College Department of Computer Applications Erode India Department of Compute Science Bengaluru India Bharath Institute of Higher Education and Research Department of Computer Science and Engineering Chennai India Sri Krishna College of Engineering and Technology Department of Artificial Intelligence and Data Science Coimbatore India College of Computing and Information Sciences Univesity of Technology and Applied Sciences Information Technology Department Ibri Oman

ISBN: (纸本)9798350385793

Breast cancer poses a significant threat to women's health, being a leading cause of cancer-related mortality among female population. In recent years, machine learning has emerged as a promising approach in medical field, particularly in detection and classification tasks. However, existing algorithms often exhibit suboptimal accuracy, necessitating improved methodologies. This research presents a novel approach using a Modified Support Vector Machine (MSVM) for breast cancer classification into benign and malignant categories. Leveraging the Wisconsin Breast Cancer dataset (WBCD), preprocessing techniques are applied to enhance data quality. Principle Component Analysis (PCA) reduces dimensionality, while linear Discriminant Analysis (LDA) extracts discriminative features crucial for classification. The proposed MSVM classifier achieves exceptional performance, with a classification accuracy of 99.42%, outperforming other existing methods such as Deep Convolutional Neural Networks and Fuzzy Rule-based Systems. These results highlight the efficacy of the MSVM approach in accurately distinguishing between benign and malignant breast cancer cases, showcasing its potential as a reliable tool for medical image analysis and cancer diagnosis. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

QUALYST: data Quality Assessment System for Thailand Open Government data

QUALYST: Data Quality Assessment System for Thailand Open Go...

引用

International Joint Conference on Computer Science and Software Engineering (JCSSE)

作者： Tanapat Samakit Chutiporn Anutariya Marut Buranarach ICT Department Computer Science & Information Management School of Engineering and Technology Asian Institute of Technology Thailand Data Science and Analytics Research Group National Electronics and Computer Technology Center Thailand

Open Government data (OGD) refers to the provision of data produced by the government to the general public, in a format that is readily readable and can be used by machines with ease. It can also promote transparency, improve decision-making, enhance accountability, create economic opportunities, and encourage civic engagement. The OGD can help citizens understand the government and its legitimacy and transparency. Thus, when the government shares its data with people, it helps to create trust by being transparent, accountable, and promoting innovative solutions that benefit everyone. However, each published dataset has no indication of its quality assessment at all; thus, making it difficult for citizens to assess the reliability of the data from the OGD. Therefore, a data quality assessment for OGD should be developed. This will help create effective datasets which in turn help users understand the data. This study proposes QUALYST, a system that assesses Thailand's OGD dataset and validates it for analytic and visualization purposes. The study focuses on designing the data storage and implementing the assessment system. Furthermore, the proposed data quality dimensions, the developed data pipeline, and the assessment process are elaborated. Finally, the prototype system is demonstrated using Thailand's OGD datasets with examples in a visualized format.

关键词：

来源：评论

学校读者我要写书评

暂无评论

N-Doped rGO-Like Carbon Prepared from Coconut Shell:Structure and Specific Capacitance

引用

Journal of Renewable Materials 2023年第4期11卷 1823-1833页

作者： Imam Khambali Budhi Priyanto Retno Asih Malik Anjelh Baqiya Muhammad Mahyiddin Ramli Nurul Huda Osman Sarayut Tunmee Hideki Nakajima Triwikantoro Mochamad Zainuri Darminto Department of Physics Faculty of Science and Data AnalyticsInstitut Teknologi Sepuluh NopemberSurabaya60111Indonesia Department of Electrical Engineering Faculty of EngineeringUniversity of Muhammadiyah MalangMalang65144Indonesia Geopolymer&Green Technology Centre of Excellence Universiti Malaysia PerlisArauPerlis02600Malaysia Applied Electromagnetic Laboratory 1 Department of PhysicsFaculty of ScienceUniversiti Putra MalaysiaSelangor43400Malaysia Synchrotron Light Research Institute(SLRI) Nakhon Ratchasima3000Thailand

An rGO−like carbon compound has been synthesized from biomass,i.e.,old coconut shell,by a carbonization process followed by heating at 400°C for 5 *** nitrogen doping was achieved by adding the urea(CH4N2O)and stirring at 70°C for 14 *** morphology and structure of the rGO-like carbon were investigated by electron microscopies and Raman *** presence of C-N functional groups was analyzed by Fourier transform infrared and synchrotron X-ray photoemission spectroscopy,while the particle and the specific capacitance were measured by particle sizer and cyclic *** highest specific capacitance of 72.78 F/g is achieved by the sample with 20%urea,having the smallest particles size and the largest surface *** corresponding sample has shown to be constituted by the appropriate amount of C–N pyrrolic and pyridinic defects.

关键词： N-doped rGO−like carbon coconut shell specific capacitance

来源：评论

学校读者我要写书评

暂无评论

Advancing Post-Hoc Case-Based Explanation with Feature Highlighting

arXiv

引用

arXiv 2023年

作者： Kenny, Eoin M. Delaney, Eoin Keane, Mark T. CSAIL Massachusetts Institute of Technology United States University College Dublin Ireland Insight Centre for Data Analytics Ireland VistaMilk SFI Research Centre Ireland

Explainable AI (XAI) has been proposed as a valuable tool to assist in downstream tasks involving human-AI collaboration. Perhaps the most psychologically valid XAI techniques are case-based approaches which display "whole" exemplars to explain the predictions of black-box AI systems. However, for such post-hoc XAI methods dealing with images, there has been no attempt to improve their scope by using multiple clear feature "parts" of the images to explain the predictions while linking back to relevant cases in the training data, thus allowing for more comprehensive explanations that are faithful to the underlying model. Here, we address this gap by proposing two general algorithms (latent and superpixel-based) which can isolate multiple clear feature parts in a test image, and then connect them to the explanatory cases found in the training data, before testing their effectiveness in a carefully designed user study. Results demonstrate that the proposed approach appropriately calibrates a user's feelings of "correctness" for ambiguous classifications in real world data on the ImageNet dataset, an effect which does not happen when just showing the explanation without feature highlighting. © 2023, CC BY.

关键词： Image enhancement

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：