检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Aghdam, Saeideh Niksirat Hossayni, Sayyed Ali Sadeh, Erfan Khedersolh Khozouei, Nasim Bidgoli, Behrouz Minaei Department of Computer Engineering Iran University of Science and Technology Tehran Iran Data Mining Lab School of Computer Engineering Iran University of Science & Technology Tehran Iran Department of computer Engineering Faculty of Engineering Yasouj University Yasouj Iran

Semantic role labeling (SRL) is the process of detecting the predicate-argument structure of each predicate in a sentence. SRL plays a crucial role as a pre-processing step in many NLP applications such as topic and concept extraction, question answering, summarization, machine translation, sentiment analysis, and text mining. Recently, in many languages, unified SRL dragged lots of attention due to its outstanding performance, which is the result of overcoming the error propagation problem. However, regarding the Persian language, all previous works have focused on traditional methods of SRL leading to a drop in accuracy and imposing expensive feature extraction steps in terms of financial resources, time and energy consumption. In this work, we present an end-to-end SRL method that not only eliminates the need for feature extraction but also outperforms existing methods in facing new samples in practical situations. The proposed method does not employ any auxiliary features and shows more than 16 (83.16) percent improvement in accuracy against previous methods in similar circumstances. © 2023, CC BY-NC-ND.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

High Dynamic Collaborative Team Query via Multi-Fuzzy-Constrained Graph Pattern Matching

High Dynamic Collaborative Team Query via Multi-Fuzzy-Constr...

引用

IEEE International Conference on Cloud Computing and Big data Analysis (ICCCBDA)

作者： Tao Hu Zan Zhang Chenyang Bu Lei Li Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) School of Computer Science and Information Engineering Hefei University of Technology Hefei China

ISBN: (数字)9798350373554

ISBN: (纸本)9798350373561

Graph pattern matching is a technique widely used in various fields such as protein structure analysis, social group querying, and expert localization. This technique involves finding matching subgraphs in large social networks that align with the patterns specified in the pattern graph. In this paper, we focus on a specific sub-problem in social group querying, known as the cooperative team query, which arises from practical applications, where the nodes in the pattern graph and the data graph represent team member entities, while the edges represent their social relationships. We note that the requirements of many teams in the real world are dynamic, necessitating iterative computation for graph pattern matching using traditional methods. To address this challenge in highly dynamic systems, we propose a graph pattern matching method based on core pattern graph matching cache. This approach involves extracting the core pattern graph, and comprising core team members based on the characteristics of cooperative teams. The core graph-based matching cache enables the second half of the algorithm to operate on an order-of-magnitude smaller graph, significantly improving efficiency. Additionally, the multi-threaded approach fully leverages hardware resources, synchronizing multiple matching result of the core pattern graph to reduce matching time. Experimental results on three real social network datasets demonstrate that our proposed algorithm, Core Pattern Graph Matching Cache-based Multi-threaded Exploration (CCMTE), significantly outperforms existing methods in terms of efficiency.

关键词： Proteins Location awareness Social networking (online) Social groups Heuristic algorithms Knowledge graphs Hardware

来源：评论

学校读者我要写书评

暂无评论

SKETCH2MANGA: Shaded Manga Screening from Sketch with Diffusion Models

SKETCH2MANGA: Shaded Manga Screening from Sketch with Diffus...

引用

IEEE International Conference on Image Processing

作者： Jian Lin Xueting Liu Chengze Li Minshan Xie Tien-Tsin Wong School of Computing and Information Sciences Saint Francis University Department of Computer Science and Engineering The Chinese University of Hong Kong Department of Data Science and Artificial Intelligence Monash University

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

While manga is a popular entertainment form, creating manga is tedious, especially adding screentones to the created sketch, namely manga screening. Unfortunately, there is no existing method that tailors for automatic manga screening, probably due to the difficulty in generating shaded high-frequency screentones of high-quality. Classic manga screening approaches generally require user input to provide screentone exemplars or a reference manga image. Recent deep learning models enable automatic generation by learning from a large-scale dataset. However, the state-of-the-art models still fail to generate high-quality shaded screentones due to the lack of a tailored model and high-quality manga training data. In this paper, we propose a novel sketch-to-manga framework that first generates a color illustration from the sketch and then generates a screentoned manga based on the intensity guidance. Our method significantly outperforms existing methods in generating high-quality manga with shaded high-frequency screentones.

关键词： Deep learning Image color analysis Training data Entertainment industry Diffusion models Animation data models

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Logistic Regression and Decision Tree Models for Lung Cancer Prediction Using Survey data

Evaluation of Logistic Regression and Decision Tree Models f...

引用

Electronic Systems and Intelligent Computing (ICESIC), International Conference on

作者： K E Narayana Jayashree K ThavaVinu A M.Sindhuja Jaeyalakshmi M Department of Information Technology Rajalakshmi Engineering College Chennai Tamilnadu India Department of Artificial Intelligence and Data Science Panimalar Engineering College Chennai Tamilnadu India Department of Information Technology Prathyusha Engineering College Chennai Department of Computer Science and Engineering Acharya University Karakul Uzbekistan Department Of Computer Science And Engineering Rajalakshmi Engineering College Chennai India

ISBN: (数字)9798331522988

ISBN: (纸本)9798331522995

Lung cancer is one of the most deadly and ubiquitous forms of cancer globally. Early detection can make a significant difference in survival rates, prognosis, etc. Background The present study compares the performance of logistic regression and decision trees using a survey-based dataset for predicting lung cancer. This dataset has a total of 284 cases with 16 features; behavioral patterns, symptomatic data, and demographic details. Logistic regression is a binary classification algorithm that uses input features to model the probability of lung cancer presence given these input features using for example a sigmoid function. Using Decision Trees can identify significant fields in a dataset while reducing Gini Impurity for models that categorize patients based on feature values. The performance of both models is evaluated according to accuracy, F1-score, precision, and recall measures. From the preliminary results, it looks like the Decision Tree works a little better than the logistic regression model which gets an accuracy of 94%, but this one does with more accuracy (97%). This result emphasizes the inclusion of logistic regression within this context, as it may be able to predict lung cancer with greater accuracy. Additionally, to ensure the generalization and robustness of the model, further investigation and trials will focus on optimizing performance through ensemble approaches, hyperparameter tuning, and cross-validation. This comparative analysis demonstrates the effectiveness of machine learning techniques in developing prediction models for early lung cancer detection, an important step toward a quick and appropriate intervention.

关键词： Surveys Logistic regression Accuracy Computational modeling Lung cancer Predictive models Robustness Decision trees Prognostics and health management Tuning

来源：评论

学校读者我要写书评

暂无评论

Research on Question Matching of Operation System FAQ with Knowledge Graph and Image Information 3

Research on Question Matching of Operation System FAQ with K...

引用

2022 3rd International Conference on computer Information and Big data Applications, CIBDA 2022

作者： Zhao, Haomin Liu, Yu Gu, Jinguang College of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan China Key Laboralory of Intelligent Information Processing and Real-time Industrial System in Hubei Province Hubei Wuhan China Institute of Big Data Science and Engineering Wuhan University of Science and Technology Hubei Wuhan China

ISBN: (纸本)9783800758760

The FAQ system is to match the questions asked by the user with the questions in the FAQ library, and subsequently return the answers to the questions according to the smenatic similarity between questions. The existing matching methods of question pair are not specially designated for the OS domain and do not incorporate domain knowledge. The screenshots of Operating System provided by user usually contain important information, which can be uesed to improve the effectiveness of question matching method. In this paper, we evaluate the important of text in image with the highlighted evaluation, location evaluation, and text evaluation, and filter out important text for question matching. In order to use knowledge of Operation System, we introduce a pretraining model incorporating the domain knowledge that can be used for problem matching. In the experiment, the method with knowledge graph and image information can fully improve the accuracy rate, recall rate and F1 score of the matching reuslts compared to the mainstream method. © VDE VERLAG GMBH - Berlin - Offenbach.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

LearningFlow: Automated Policy Learning Workflow for Urban Driving with Large Language Models

arXiv

引用

arXiv 2025年

作者： Peng, Zengqi Wang, Yubin Han, Xu Zheng, Lei Ma, Jun Robotics and Autonomous Systems Thrust The Hong Kong University of Science and Technology Guangzhou China Data Science and Analytics Thrust The Hong Kong University of Science and Technology Guangzhou China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology China

Recent advancements in reinforcement learning (RL) demonstrate the significant potential in autonomous driving. Despite this promise, challenges such as the manual design of reward functions and low sample efficiency in complex environments continue to impede the development of safe and effective driving policies. To tackle these issues, we introduce LearningFlow, an innovative automated policy learning workflow tailored to urban driving. This framework leverages the collaboration of multiple large language model (LLM) agents throughout the RL training process. LearningFlow includes a curriculum sequence generation process and a reward generation process, which work in tandem to guide the RL policy by generating tailored training curricula and reward functions. Particularly, each process is supported by an analysis agent that evaluates training progress and provides critical insights to the generation agent. Through the collaborative efforts of these LLM agents, LearningFlow automates policy learning across a series of complex driving tasks, and it significantly reduces the reliance on manual reward function design while enhancing sample efficiency. Comprehensive experiments are conducted in the high-fidelity CARLA simulator, along with comparisons with other existing methods, to demonstrate the efficacy of our proposed approach. The results demonstrate that LearningFlow excels in generating rewards and curricula. It also achieves superior performance and robust generalization across various driving tasks, as well as commendable adaptation to different RL algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Improved Power Conversion Efficiency and Stability of Perovskite Solar Cells Induced by Dual Interface Passivation

Improved Power Conversion Efficiency and Stability of Perovs...

引用

2023 International Conference on Optoelectronic Materials and Devices, ICOMD 2023

作者： Guan, Nianci Han, Qizhuo Institute of Biomedical Materials & Engineering Northwestern Polytechnical University Xi'an710072 China The School of Computer Science National Engineering Laboratory for Integrated Aero-Space-Ground- Ocean Big Data Application Technology Shaanxi Provincial Key Laboratory of Speech and Image Information Processing Northwestern Polytechnical University Xi’an710072 China

ISBN: (纸本)9781510674509

Efficient and stable Perovskite solar cells (PSCs) have been successfully produced using a dual-layer modified (DLM) perovskite thin film. This method simultaneously modifies both the bottom (SnO2/perovskite) and top (perovskite/SpiroOMeTAD) interfaces of the perovskite. The crystallinity of the perovskite film is enhanced after the DLM treatment. Additionally, thin barrier layers are formed on both its bottom and top surfaces, which reduce surface defect density and non-radiative recombination of carriers. The bottom and top modifier layers prevent direct contact between the hole transport layer and the electron transport layer, forming a high-energy barrier that promotes carrier transmission in PSCs. Consequently, the methylammonium acetate (MAAc)-PSC achieves an efficiency of 21.96%. © 2024 SPIE. All rights reserved.

关键词： Perovskite solar cells

来源：评论

学校读者我要写书评

暂无评论

Exploring Advanced Edge Techniques in AI to Develop High-Performance Information Retrieval Systems

Exploring Advanced Edge Techniques in AI to Develop High-Per...

引用

2023 International Conference on Power Energy, Environment and Intelligent Control, PEEIC 2023

作者： Kumar, Jambi Ratna Raja Mondal, Dipannita Ravivarman, G. Latha, B. Yadav, Gitanjali B. Dwivedi, Shivangi Genba Sopanrao Moze College of Engineering Department of Computer Engineering Maharashtra Pune India Dr. D.Y. Patil College of Engineering and Innovation Artificial Intelligence and Data Science Department Talegaon India Karpagam Academy of Higher Education Department of Electrical and Electronics Engineering Coimbatore641021 India Prince Shri Venkateshwara Padmavathy Engineering College Department of Information Technology Chennai India Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Mangalayatan University Department of Commerce Jabalpur India

ISBN: (纸本)9798350357769

Information retrieval (IR) is an essential aspect of modern-day generation, especially with the fast increase and expansion of the net and its related technologies. IR aims to broaden systems that can correctly and appropriately retrieve applicable statistics from considerable data, assisting customers in their search and records accumulating wishes. AI has performed a tremendous function in advancing IR techniques, making systems more innovative and efficient in retrieving data. However, with the ever-growing extent of facts on the net and the want for real-time admission to statistics, there may be a growing desire for side computing in IR systems. Area computing refers to the processing and garage of records at the brink of the community instead of sending them to a critical area for processing. This method gives numerous advantages, including reduced latency, stepped-forward information privacy and safety, and efficient use of community bandwidth. In recent years, researchers have explored superior side strategies in AI to broaden high-overall performance IR systems. These techniques include aspect caching, facet gadget mastering, and edge-based statistics filtering, Part caching entails storing frequently accessed data at the community's edge, reducing the need to retrieve information from a critical server. This technique can improve IR systems' performance by reducing latency and community congestion. © 2023 IEEE.

关键词： appreciably congestion numerous performance processing

来源：评论

学校读者我要写书评

暂无评论

An Efficient Graphics data Retrieval Method Based on data Conversion Schemes

An Efficient Graphics Data Retrieval Method Based on Data Co...

引用

International Conference on Electronics, Information and Communications (ICEIC)

作者： Nakhoon Baek School of Computer Science and Engineering Kyungpook National University Daegu Korea Graduate School of Data Science Kyungpook National University Daegu Korea Data-Driven Intelligent Mobility ICT Research Center Kyungpook National University Daegu Korea

ISBN: (数字)9798331510756

ISBN: (纸本)9798331510763

Modern computer graphics systems usually manage a set of internal data to store control parameters and all kind of graphics data. The behind problem on these graphics system data is that they are frequently updated and retrieved with variety of data types, even they are initially stored as specific data types. To support these updates and retrievals with various data types, modern graphics systems typically use data type conversion features, and even in the worst cases, they should provide all combinations of internally stored data types and newly provided or retrieved data types. In this paper, we show how to efficiently provide all the required combinations of data type conversions, with motivations, analysis, and overall designs. We also show typical type conversion scenarios, with specific API function examples. Our design shows that it can improve the internal architecture and the internal efficiency of modern computer graphics systems. In its implementation, we use C++std:: map container for fast lookup of the best-suitable conversion function. This overall scheme was integrated in our existing systems, and shows its feasibility and correctness.

关键词： data conversion Pipelines Switches computer graphics C++ languages computer architecture Containers data retrieval

来源：评论

学校读者我要写书评

暂无评论

Robust Analysis of Visual Question Answering Based on Irrelevant Visual Contextual Information 5th

Robust Analysis of Visual Question Answering Based on Irrele...

引用

5th International Conference on Artificial Intelligence in China, AIC 2023

作者： Qin, Jun Zhang, Zejin Ye, Zheng Liu, Zhou Cheng, Yong College of Computer Science South-Central Minzu University Wuhan430074 China Hubei Provincial Engineering Research Center for Intelligent Management of Manufacturing Ente rprises Wuhan430074 China Beijing Qingtai Data Technology Co. Ltd. Beijing100000 China

ISBN: (纸本)9789819975440

The growth of social media data has led to the development of VQA (Visual Question Answering) tasks, and the problem of VQA model robustness has emerged as a new issue in the public eye. In this work, we extend the generalization of the SwapMix [1] to the VQA-v2 benchmark dataset by solving the problem that it is only applicable to a specific manually annotated dataset. Then we propose semantic correlation to solve the problem of whether the problem is related to the entities in the images. Finally, we employ SwapMix’s mainstream model MCAN on the VQA-v2 dataset for data augmentation to further improve its model robustness, by this step, we improve the accuracy of the model after performing attentional perturbation from 35.34 to 44.01%. The experiments demonstrate that the method proposed in this paper is effective in diagnosing model robustness and regulating overdependence on visual context. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Semantics

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：