检索结果-内蒙古大学图书馆

5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022

作者： Lin, Hong Tse, Rita Tang, Su-Kit Qiang, Zhen-Ping Pau, Giovanni Macao Polytechnic University Faculty of Applied Sciences China Macao Polytechnic University Eng. Res. Ctr. of Appl. Technol. on Mach. Transl. and Artif. Intelligence of Ministry of Education China Southwest Forestry University College of Big Data and Intelligent Engineering KunMing China University of Bologna Department of Computer Science and Engineering-DISI Bologna Italy University of California Samueli Computer Science Department Los Angeles United States

ISBN: (数字)9781665499163

ISBN: (纸本)9781665499163

Few-shot learning is good solution for plant disease recognition which can generalize to new categories by using few samples. However, the features extracted from few shots are limited. Attention is a technique for focusing on the significant features which can help to obtain better feature representation. In this work, we use a naive metric-based few-shot learning network as the baseline method, exploit the effect of different kinds of attention module: channel attention, spatial attention and hybrid attention. In experiments, we choose the representative modules of each attention category to show their effects in few-shot learning paradigm: SE, ASPP, CBAM and Triplet Attention. We conduct experiments with two data settings of PlantVillage, and illustrate the usage these attention modules in Residual Networks. The results indicate that the different attention modules can improve recognition accuracy to varying degrees. Attention can be used as effective improvement of feature representation under few-shot condition. © 2022 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

A Review on Bayesian Methods for Uncertainty Quantification in Machine Learning Models Enhancing Predictive Accuracy and Model Interpretability

A Review on Bayesian Methods for Uncertainty Quantification ...

引用

Intelligent Cyber Physical Systems and Internet of Things (ICoICI), International Conference on

作者： Moses Makuei Jiet Prateek Verma Aahash Kamble Chetan Puri Department of Computer Science and Design Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Sawangi Wardha Maharashtra India Department of Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Sawangi Wardha Maharashtra India Department of Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Sawangi Wardha Maharashtra India

ISBN: (数字)9798331540661

ISBN: (纸本)9798331540678

This research study reviews the statistical fundamentals of machine learning with a focus on Bayesian methods to quantify the uncertainty in model predictions. Bayesian statistics provides a framework for incorporating prior knowledge, updating beliefs, and expressing uncertainty in predictions. This research study will explore Bayesian techniques applied to various aspects of machine learning, including regression, classification, deep learning, and ensemble methods.

关键词： Uncertainty Accuracy Reviews Computational modeling Pipelines Predictive models Probabilistic logic Bayes methods Internet of Things Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Enabling Surrogate-Assisted Evolutionary Reinforcement Learning via Policy Embedding 1

引用

17th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2022

作者： Tang, Lan Li, Xiaxi Zhang, Jinyuan Li, Guiying Yang, Peng Tang, Ke Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Faculty of Engineering Shenzhen MSU-BIT University Shenzhen518172 China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen518055 China Department of Statistics and Data Science Southern University of Science and Technology Shenzhen518055 China

ISBN: (数字)9789819915491

ISBN: (纸本)9789819915484

Evolutionary Reinforcement Learning (ERL) that applying Evolutionary Algorithms (EAs) to optimize the weight parameters of Deep Neural Network (DNN) based policies has been widely regarded as an alternative to traditional reinforcement learning methods. However, the evaluation of the iteratively generated population usually requires a large amount of computational time and can be prohibitively expensive, which may potentially restrict the applicability of ERL. Surrogate is often used to reduce the computational burden of evaluation in EAs. Unfortunately, in ERL, each individual of policy usually represents millions of weights parameters of DNN. This high-dimensional representation of policy has introduced a great challenge to the application of surrogates into ERL to speed up training. This paper proposes a PE-SAERL Framework to at the first time enable surrogate-assisted evolutionary reinforcement learning via policy embedding (PE). Empirical results on 5 Atari games show that the proposed method can perform more efficiently than the four state-of-the-art algorithms. The training process is accelerated up to 7x on tested games, comparing to its counterpart without the surrogate and PE. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Enhance Multi-domain Sentiment Analysis of Review Texts through Prompting Strategies

arXiv

引用

arXiv 2023年

作者： Wang, Yajing Luo, Zongwei Hong Kong Baptist University BNU-HKBU United International College Faculty of Science and Technology Department of computer science Hongkong Zhuhai China BNU-UIC Institute of AI and Future Networks Artificial Intelligence and Data Science Research Hub Beijing Normal University BNU-HKBU United International College Zhuhai China

—Large Language Models (LLMs) have made significant strides in both scientific research and practical applications. Existing studies have demonstrated the state-of-the-art (SOTA) performance of LLMs in various natural language processing tasks. However, the question of how to further enhance LLMs’ performance in specific task using prompting strategies remains a pivotal concern. This paper explores the enhancement of LLMs’ performance in sentiment analysis through the application of prompting strategies. We formulate the process of prompting for sentiment analysis tasks and introduce two novel strategies tailored for sentiment analysis: RolePlaying (RP) prompting and Chain-of-thought (CoT) prompting. Specifically, we also propose the RP-CoT prompting strategy which is a combination of RP prompting and CoT prompting. We conduct comparative experiments on three distinct domain datasets to evaluate the effectiveness of the proposed sentiment analysis strategies. The results demonstrate that the adoption of the proposed prompting strategies leads to a increasing enhancement in sentiment analysis accuracy. Further, the CoT prompting strategy exhibits a notable impact on implicit sentiment analysis, with the RP-CoT prompting strategy delivering the most superior performance among all strategies. Copyright © 2023, The Authors. All rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

High-purity single-photon generation based on cavity QED

引用

Physical Review Research 2025年第1期7卷 013251-013251页

作者： Seigo Kikura Rui Asaoka Masato Koashi Yuuki Tokunaga Department of Applied Physics Graduate School of Engineering The University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo 113-8656 Japan Faculty of Science and Engineering Waseda University 3-4-1 Okubo Shinjuku-ku Tokyo 169-8585 Japan Computer and Data Science Laboratories NTT Corporation Musashino 180-8585 Japan Photon Science Center Graduate School of Engineering The University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo 113-8656 Japan

We propose a scheme for generating a high-purity single photon on the basis of cavity QED. This scheme employs an atom as a four-level system and the structure allows the suppression of the reexcitation process due to the atomic decay, which is known to significantly degrade the single-photon purity in state-of-the-art photon sources using a three-level system. Our analysis shows that the reexcitation probability arbitrarily approaches zero without sacrificing the photon generation probability when increasing the power of a driving laser between two excited states. This advantage is achievable by using current cavity-QED technologies. Our scheme can contribute to developing distributed quantum computation or quantum communication with high accuracy.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Link Prediction with Contextualized Self-Supervision

arXiv

引用

arXiv 2022年

作者： Zhang, Daokun Yin, Jie Yu, Philip S. The Department of Data Science & AI Faculty of Information Technology Monash University Australia The Discipline of Business Analytics The University of Sydney Australia Department of Computer Science University of Illinois Chicago United States

Link prediction aims to infer the link existence between pairs of nodes in networks/graphs. Despite their wide application, the success of traditional link prediction algorithms is hindered by three major challenges—link sparsity, node attribute noise and dynamic changes—that are faced by many real-world networks. To address these challenges, we propose a Contextualized Self-Supervised Learning (CSSL) framework that fully exploits structural context prediction for link prediction. The proposed CSSL framework learns a link encoder to infer the link existence probability from paired node embeddings, which are constructed via a transformation on node attributes. To generate informative node embeddings for link prediction, structural context prediction is leveraged as a self-supervised learning task to boost the link prediction performance. Two types of structural context are investigated, i.e., context nodes collected from random walks vs. context subgraphs. The CSSL framework can be trained in an end-to-end manner, with the learning of model parameters supervised by both the link prediction and self-supervised learning tasks. The proposed CSSL is a generic and flexible framework in the sense that it can handle both attributed and non-attributed networks, and operate under both transductive and inductive link prediction settings. Extensive experiments and ablation studies on seven real-world benchmark networks demonstrate the superior performance of the proposed self-supervision based link prediction algorithm over state-of-the-art baselines, on different types of networks under both transductive and inductive settings. The proposed CSSL also yields competitive performance in terms of its robustness to node attribute noise and scalability over large-scale networks. © 2022, CC BY-NC-ND.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

A DWT-Based Model with CNN-based Decision Fusion Strategy for Medical Image Encryption Scheme for Healthcare Network

A DWT-Based Model with CNN-based Decision Fusion Strategy fo...

引用

Smart Technologies, Communication and Robotics (STCR)

作者： G. Ramkumar Osama Jamal Jamil Abed Al Jawad J. Lefty Joyson P. Nancy Navdeep Singh Rowsonara Begum Department of ECE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Saveetha University Chennai India Faculty of Economic and Administrative Sciences BIT Zarqa University Zarqa Jordan College of Business Administration University of Business and Technology Jeddah Saudi Arabia Department of Computer Science and Engineering J.P. College of Engineering Tenkasi School of Electronics and Electrical Engineering Lovely Professional University India Department of Computer Science & Engineering (Data Science) MLR Institute of Technology Dundigal Hyderabad Telengana

ISBN: (数字)9798350357530

ISBN: (纸本)9798350357547

Telemedicine and digital health are expanding rapidly, increasing the demand for secure and precise transmission of medical images. This study introduces an innovative hybrid model that combines DWT, CNN, and encryption techniques for safe image processing. The Proposed DWR-CNN model secures image embedding, hybrid encryption, and deep learning classification techniques. Medical images are concealed within a reference image using methods such as SVD to maintain their confidentiality while remaining unaltered. The image is subsequently transformed using DWT to enhance its resilience against attacks. A blend of AES and ECC protects the image transfer. VGG16 and YOLOv8 are to extract features and identify errors. The DWT-CNN model encourages precision and robust safety in evaluations using medical imaging datasets.

关键词： Deep learning Accuracy Telemedicine Watermarking Transforms Elliptic curve cryptography Feature extraction Discrete wavelet transforms Encryption Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework for Detection of Digital Face Video Manipulation using Deep Learning

A Novel Framework for Detection of Digital Face Video Manipu...

引用

Computing and Information Technology (ICCIT-1441), 2020 International Conference on

作者： Sanskriti Chandra Shivam Saxena Santosh Kumar Mithilesh Kumar Chaube Srinivas K G Saeed Hamood Alsamhi Edward Curry Abdu Saif Department of Data Science and Artificial Intelligence IIIT-Naya Raipur Chhattisgarh India Department of Computer Science and Engineering IIIT-Naya Raipur Chhattisgarh India Department of Mathematical Sciences IIIT-Naya Raipur Chhattisgarh India Insight SFI Research Centre for Data Analytics University of Galway Galway Ireland Faculty of Engineering & Information Technology Taiz Yemen

Digital face manipulation and classification have recently attracted the attention of academia and industry worldwide. Researchers have developed deep learning and computer vision techniques for detecting face manipulations, and it has become a challenging task to differentiate between authentic and manipulated face images manually. The challenge results in the decline of authenticity in digital media content. In this paper, we propose a framework for the classification of manipulating face images using the EfficientNet learning model. The proposed framework takes four digital facial forgeries: Face-Swap, Face-2-Face, DeepFakes, and neural textures. Multiple manipulation techniques are used to process manipulated faces, such as the Blaze-face tracking method, to determine the locations of the face images and pixel coordinates. The proposed framework is used first to identify the type of face manipulation and then to perform detection of the tampered regions in the face images. The proposed framework provided an automated benchmark that considers all four modification techniques in a realistic situation. The results show that the proposed framework outperforms existing approaches regarding accuracy and efficiency. Furthermore, the proposed framework is suitable for detecting digital face video manipulation in various applications, including forensics and security.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Correction:Noise-Filtering Enhanced Deep Cognitive Diagnosis Model for Latent Skill Discovering

引用

Intelligent Automation & Soft Computing 2024年第5期39卷 985-986页

作者： Jing Geng Huali Yang Shengze Hu National Engineering Research Center of Educational Big Data Central China Normal UniversityWuhan430079China Faculty of Artificial Intelligence in Education Central China Normal UniversityWuhan430079China School of Computer Science and Artificial Intelligence Wuhan Textile UniversityWuhan430079China

In the article“Noise-Filtering Enhanced Deep Cognitive Diagnosis Model for Latent Skill Discovering”by Jing Geng,Huali Yang and Shengze Hu(Intelligent Automation&Soft Computing,2023,Vol.37,No.2,***:10.32604/iasc.2023.038481),the References[1-2],[4-12],and[23-29]were not appropriately aligned with the context of the main text.

关键词： Deep Automation app

来源：评论

学校读者我要写书评

暂无评论

Automatic Section Classification in Spanish Clinical Narratives Using Chunked Named Entity Recognition

Automatic Section Classification in Spanish Clinical Narrati...

引用

2023 Iberian Languages Evaluation Forum, IberLEF 2023

作者： Carvallo, Andrés Rojas, Matías Muñoz-Castro, Carlos Aracena, Claudio Guerra, Rodrigo Pizarro, Benjamín Dunstan, Jocelyn National Center for Artificial Intelligence Santiago Chile Faculty of Physical and Mathematical Sciences Universidad de Chile Santiago Chile Department of Computer Science Pontificia Universidad Católica de Chile Santiago Chile Institute for Mathematical Computing Pontificia Universidad Católica de Chile Santiago Chile Center for Mathematical Modeling Santiago Chile Millenium Institute Foundational Research on Data Santiago Chile

The extraction and classification of important information from Spanish Electronic Clinical Narratives (ECNs) can be challenging due to the complexity of the clinical text and the limited availability of labeled data. In this paper, we introduce a chunked Named Entity Recognition model designed to parse and classify sections of ECNs into predefined categories. The model aims to improve section identification and classification accuracy within ECNs in the context of the IberLEF ClinAIS Task. Our system achieves a promising performance, obtaining a weighted B2 score of.6958, demonstrating its capability to accurately distinguish borders and boundaries between sections. The paper concludes with a comprehensive analysis of the results, discussing potential implications and suggesting directions for further improvements in clinical text analysis. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Classification (of information)

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：