检索结果-内蒙古大学图书馆

Graph decision transformer for offline reinforcement learning

science China(Information sciences) 2025年第6期68卷 395-396页

作者： Shengchao HU Li SHEN Ya ZHANG Dacheng TAO School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai Artificial Intelligence Laboratory Shanghai AI Laboratory School of Cyber Science and Technology Shenzhen Campus of Sun Yat-sen University School of Computer and Data Science Nanyang Technological University

Recent advances [1, 2] in offline reinforcement learning(RL)have taken a new perspective on the problem, departing from conventional methods that concentrate on learning value functions or policy gradients. Instead, the problem is viewed as a generic sequence modeling task, where past experiences consisting of state-action-reward triplets are input to the Transformer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FoSoHA-Net: Deep Learning for Accurate Breast Cancer Classification Leveraging Hybrid Attention Mechanisms 2

FoSoHA-Net: Deep Learning for Accurate Breast Cancer Classif...

引用

2nd International Conference on Intelligent Perception and Computer Vision, CIPCV 2024

作者： Addo, Daniel Al-Antari, Mugahed A. Zhou, Shijie Ashalley, Eric Muoka, Gladys Wavinya Nartey, Obed T. University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu610054 China Sejong University AISSLab Department of Artificial Intelligence and Data Science Seoul Korea Republic of University of Electronic Science and Technology of China Chengdu610054 China Sino-British Collaborations ChengduUniversity of Technology of China Erxianqiao Campus Chengdu610059 China

ISBN: (纸本)9798350360097

Breast cancer diagnosis is crucial for timely treatment and management. This study introduces FoSoHA-Net, a novel methodology for precise breast cancer classification using histopathological images. FoSoHA-Net integrates a hybrid attention module (HAM) and depthwise separable convolution to enhance feature extraction and improve classification accuracy. The hybrid attention module combines first-order pooling attention (FoPA) and second-order pooling attention (SoPA) to leverage global and local image information, augmenting the model's discriminative power. Through comprehensive evaluation of the BreaKHis dataset, FoSoHA-Net demonstrates superior performance in accurately classifying histopathological images across various magnification levels. Comparative analysis against established pre-trained models further validates the effectiveness of FoSoHA-Net in breast cancer classification tasks. Overall, FoSoHA-Net shows promise in advancing breast cancer diagnosis through innovative AI-driven approaches. © 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

Plant Digital Twins Based on Model Phenotyping and Functional-Structural Plant Modeling 4

Plant Digital Twins Based on Model Phenotyping and Functiona...

引用

4th IEEE International Conference on Digital Twins and Parallel intelligence, DTPI 2024

作者： Liu, Zhiqing Wang, Xiujuan Hua, Jing Wang, Haoyu Huo, Qirun Kang, Mengzhen Capital Normal University Information Engineering College Beijing China Institute of Automation Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing China Macau University of Science and Technology Faculty of Innovation Engineering China

ISBN: (纸本)9798350349252

In this digital age, digital twin technology has been widely applied in various fields. However, its use in agriculture is still in the early stages. Existing literature on plant digital twins indicates that they have a limited capacity to interact with real plants or to predict the complete plant growth process. This paper aims to propose a new approach to plant digital twin by combining them with actual plant phenotyping technology. By obtaining plant phenotypic data and integrating them with the plant model, we aim at predicting the entire plant growth process, thereby achieving a dynamic plant digital twin. © 2024 IEEE.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

Product Quality Enhancement in Social Media using Emotion-Enhanced Bert (EE-BERT) Model

Product Quality Enhancement in Social Media using Emotion-En...

引用

Self Sustainable artificial intelligence Systems (ICSSAS), International Conference on

作者： V S Raj Kumar T Kumaresan V Mythily N Raghavendran Department of Artificial Intelligence and Data science Bannari Amman Institute of Technology Sathyamangalam India Department of Computer Science and Engineering Bannari Amman Institute of Technology Sathyamangalam India Department of Computer Science and Engineering Nandha Engineering College Erode India Department of Artificial Intelligence and Data science RMK college of Engineering and Technology Chennai India

ISBN: (数字)9798350368413

ISBN: (纸本)9798350368420

Twitter plays an important role in understanding the consumer sentiment about the products. The advanced analytics and Natural Language Processing (NLP) are used to extract actionable insights from this data and useful for a business to improve features and address issues on time for better customer satisfaction and brand loyalty. Most of the current models suffer from a lack of effective ways to handle subtle sentiment analysis because of a lack of contextual understanding and proper feature extraction. Most traditional models cannot combine and optimize features that lead to obtaining sentiments. This leads to overfitting and problems caused by local minima. The proposed Emotion-Enhanced BERT (EE-BERT) model is an extension of the standard BERT to learn contextual embeddings in user sentiment. In this work, data preprocessing includes text cleaning, tokenization, dealing with emojis and emoticons, and lemmatization with the best quality data. The proposed work is basically a dual-stream architecture extended with butterfly optimizer. First, the advanced tokenization and semantic understanding techniques is used for extracting textual features. Second, the emotion-enhanced features extracted through emotion-hash vectorization to enhance the model’s contextual awareness in social media data. This provides a unified framework that combines the feature extraction methods to enhance the accuracy in sentiment analysis. It demonstrated with an impressive accuracy of ${9 8. 2 \%}$ on sentiment in posts and comments with 0.15 losses. The proposed work is free from overfitting and local minima in product quality enhancement.

关键词： Accuracy Social networking (online) Computational modeling Blogs Feature extraction Product design Encoding data models Quality assessment Context modeling

来源：评论

学校读者我要写书评

暂无评论

Optimizing Supply Chain Operations through Machine Learning: Opportunities and Challenges

Optimizing Supply Chain Operations through Machine Learning:...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Santhakumar, D. Soundararajan, Gopalakrishnan Chintala, Suman Bharath, E. Murthy Inumula, Krishna Chouhan, Kuldeep Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Thandalam Tamil Nadu Chennai602105 India Muscat College Ruwi Oman Business Intelligence Architect United States C K College of Engineering & Technology Anna University Department of Artificial Intelligence & Data Science Tamil Nadu Cuddalore India Maharashtra Pune411057 India Sharda School of Engineering and Technology Sharda University Department of Computer Science and Applications Greater Noida201310 India

ISBN: (纸本)9798331508685

In order to create enduring partnerships that are essential to attaining long-term economic success, supply chain management, or SCM, is essential. Strict standards and decision-making procedures are necessary for efficient SCM, and they have a big influence on the final results. In order to efficiently manage inventory levels and logistical procedures, this study offers a complex ML system that combines demand forecasts and optimisation methods. For predicting demand, the approach uses a Generative Adversarial Networks (GAN) model, taking advantage of its capacity to process time-series data and identify intricate trends. The algorithm achieves an impressive 96.4% forecasting of demand accuracy by examining extensive historical sales data and a variety of supply chain variables. In order to optimise inventory rules, the investigation also uses optimisation techniques, particularly Genetic Algorithms (GA) in conjunction with Simulated Annealing (SA). The model demonstrated significant improvements when implemented to an actual commercial logistics system. Notably, it reduced storage expenses by 19% and increased order fulfillment rates by 24%, proving its capacity for combining service standards with financial efficiency. The findings highlight the significant impact of ML on improving supply chain efficiency and show how it can result in significant cost savings and improve service quality. © 2025 IEEE.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

Optimizing Resource Management and data Security in Cloud Computing Environments 3

Optimizing Resource Management and Data Security in Cloud Co...

引用

3rd International Conference for Advancement in technology, ICONAT 2024

作者： Shri, S.Jothi Karthiyayini, G. Vignesh, L.S. Upender, Talluri Shobana, D. Patra, Ladi Sandip Kumar Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Ramco Institute of Technology Department of CSE Tamil Nadu Rajapalayam India Nadar Saraswathi College of Engineering and Technology Department of Artificial Intelligence and Data Science Theni India CMR College of Engineering and Technology Medchal Department of CSE Telangana Hyderabad India Rajalakshmi Engineering College Department of Mechatronics Engineering Chennai India MLR Institute of Technology Department of ECE Hyderabad India

ISBN: (纸本)9798350354171

The quick uptake of cloud computing has completely changed how companies run since it offers flexible and scalable resources that promote productivity and creativity. However, the dynamic and complex nature of cloud environments presents significant challenges in optimizing resource management and ensuring robust data security. This paper investigates advanced strategies and methodologies for enhancing resource allocation, virtualization, and scheduling to maximize performance and cost-efficiency in cloud infrastructures. Key techniques explored include dynamic scaling, load balancing, VM migration, containerization, and cost-effective resource usage through spot and reserved instances. The important facets of cloud computing data security, such as encryption, identity and access management (IAM), data loss prevention (DLP), and intrusion detection and prevention systems (IDPS), are also covered in tandem by this research. The study offers novel approaches for reducing security threats and guaranteeing data integrity by fusing cutting-edge technology like blockchain and machine intelligence. The comprehensive analysis aims to provide actionable insights and practical recommendations for IT professionals and organizations striving to optimize their cloud computing operations. By balancing resource management efficiency with stringent security measures, this research contributes to the development of a more secure and efficient cloud ecosystem. The results emphasise the significance of a comprehensive strategy for managing cloud systems, where data security and performance optimisation work together to provide durable and sustainable cloud computing environments. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Avian Identification: Utilizing Xception Algorithm for Bird Breed Discrimination 2

Avian Identification: Utilizing Xception Algorithm for Bird ...

引用

2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Raja, S.R. Suganthi, P. Vivekanandan, Munian Vanitha, N. Vivekanandan, G. Venu, Nookala Centre for Open and Digital Education Chennai India Sri Sai Ram Institute of Technology Department of Computer Science and Engineering Chennai India Rajalakshmi Institute of Technology Artificial Intelligence and Data Science Chennai India Sri Sairam Institute of Technology Department of Computer Science and Engineering Tamil Nadu Chennai 44 India Sri Sairam Institute of Technology Department Computer Science and Engineering Chennai India Madhya Pradesh Gwalior474 005 India

ISBN: (纸本)9798350384277

In this ground breaking project, we delve into the fascinating realm of ornithology through an extensive dataset comprising 507 distinct bird breeds and a staggering 61,250 high-resolution images. Employing cutting-edge machine learning techniques, our aim is to develop a robust classification model capable of accurately identifying bird species based on visual attributes. The dataset, meticulously curated for diversity, spans a myriad of habitats, climates, and avian characteristics. Through this expansive collection, our model not only encapsulates the beauty of various feathered species but also ensures a broad spectrum of challenges in classification, pushing the boundaries of current bird recognition systems. Our approach transcends conventional methods by leveraging state-of-the-art neural networks, harnessing the power of deep learning to discern subtle nuances in plumage, size, and distinctive markings. The model's ability to adapt and learn from this vast dataset promises breakthroughs in bird breed classification, offering insights into the intricate world of avian biodiversity. This project stands as a testament to the synergy between ornithology and artificial intelligence, fostering a deeper understanding of avian ecosystems. By avoiding plagiarism and embracing creativity, our abstract articulates the uniqueness of our endeavour, propelling the field of bird breed classification into uncharted territories. © 2024 IEEE.

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

Interpreting Doctors' Notes Using Handwriting Recognition and Deep Learning Techniques

Interpreting Doctors' Notes Using Handwriting Recognition an...

引用

International Conference on science technology engineering and Management (ICONSTEM)

作者： Maheswari G Ramya. R Babitha. S Sriram. R Jennis. M I RamPrasad. P Department of Information Technology Hindustan Institute of Technology and Science Chennai India Department of Artificial Intelligence and Data Science PSNA College of Engineering and Technology

ISBN: (数字)9798350365092

ISBN: (纸本)9798350365108

This research provides a deep learning approach and handwriting recognition to understand medical notes. The system processes and interprets textual medical notes using connectionist temporal classification (CTC) and optical character recognition (OCR) techniques. The written text is transcribed using the OCR component, and then the CTC algorithm is utilized to analyze the text and give significance to particular note portions. The suggested system's ability to correctly understand and arrange written medical information is demonstrated by training it on prescription notes from doctors taken from a dataset. According to the final forecast, the system can read medical notes with high accuracy, making medical professionals' usage and accessibility of these records easier. The suggested paradigm offers fast and precise access to patient information, which could increase the efficacy and efficiency of medical care.

关键词： Deep learning Training Handwriting recognition Accuracy Optical recording Optical character recognition Software algorithms

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approach 39

Personalized Federated Collaborative Filtering: A Variationa...

引用

39th Annual AAAI Conference on artificial intelligence, AAAI 2025

作者： Li, Zhiwei Long, Guodong Zhou, Tianyi Jiang, Jing Zhang, Chengqi Australian Artificial Intelligence Institute Faculty of Engineering and IT University of Technology Sydney Australia Department of Computer Science University of Maryland College Park United States Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University Hong Kong

ISBN: (纸本)157735897X

Federated Collaborative Filtering (FedCF) is an emerging field focused on developing a new recommendation framework with preserving privacy in a federated setting. Existing FedCF methods typically combine distributed Collaborative Filtering (CF) algorithms with privacy-preserving mechanisms, and then preserve personalized information into a user embedding vector. However, the user embedding is usually insufficient to preserve the rich information of the fine-grained personalization across heterogeneous clients. This paper proposes a novel personalized FedCF method by preserving users' personalized information into a latent variable and a neural model simultaneously. Specifically, we decompose the modeling of user knowledge into two encoders, each designed to capture shared knowledge and personalized knowledge separately. A personalized gating network is then applied to balance personalization and generalization between the global and local encoders. Moreover, to effectively train the proposed framework, we model the CF problem as a specialized Variational AutoEncoder (VAE) task by integrating user interaction vector reconstruction with missing value prediction. The decoder is trained to reconstruct the implicit feedback from items the user has interacted with, while also predicting items the user might be interested in but has not yet interacted with. Experimental results on benchmark datasets demonstrate that the proposed method outperforms other baseline methods, showcasing superior performance. Copyright © 2025, Association for the Advancement of artificial intelligence (***). All rights reserved.

关键词： Variational techniques

来源：评论

学校读者我要写书评

暂无评论

Study on Calculation of Regulated Neutron Spectrum Based on Moderator with Multi-dimensional Features

Study on Calculation of Regulated Neutron Spectrum Based on ...

引用

2024 International Conference on Materials Physics and Applications, ICMPA 2024

作者： Cao, Chenglong Cao, Pei Sun, Ming Chen, Huaijin Zhang, Haiyan Institution of Electronic Engineering National University of Defense Technology Hefei230031 China School of Artificial Intelligence and Big Data Hefei University Hefei230001 China Hefei Institutes of Physical Science Chinese Academy of Sciences Hefei230027 China

Neutron transport simulation is one of the key techniques for calculating the regulated neutron spectrum, which is extremely accurate but comes with a significant time loss and is difficult to achieve convergence when there is deep penetration. Accurate regulation of the neutron spectrum is essential for research on experimental neutronics. In this study, a fast way to compute the regulated neutron spectrum using a moderator with multi-dimensional features was developed. The response matrix with different dimensions was generated for each moderator after it first created a moderator database by classifying common shielding materials based on various dimensions (such as shape, size, substance, etc.). Finally, neutron transport modeling enabled the speedy and precise estimation of regulated neutron spectrum via matrix transformation. The results demonstrated that the mean square error (MSE) of the normalized regulated neutron spectra computed using the Monte Carlo approach and the proposed technique were able to reach the order of 10-6. The anticipated method was confirmed by equating the results with those of the Monte Carlo method under a regulation system consisting of moderators of different dimensions. Furthermore, the MSE of the regulated neutron spectrum in the case of deep penetration of the simplified thermal reactor TRIGA of the two methods in the convergent energy domain could also reach the order of 10-6, and in the divergent domain, the suggested method in this study was able to give a heuristic neutron spectrum. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Moderators

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：