检索结果-内蒙古大学图书馆

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Gurav, Aryan Sharad Karanjikar, Yathharth Munesh Bhikle, Omkar Arun Deshpande, Himani Thadomal Shahani Engineering College Department of Artificial Intelligence and Data Science Mumbai India Vidyavardhini's College of Engineering and Technology Department of Artificial Intelligence and Data Science Mumbai Vasai India

ISBN: (纸本)9798350379945

Addressing the challenge of limited data in remote sensing, this research investigates the application of Generative Adversarial Networks (GANs) to augment the EuroSat dataset. Four GAN variants (Info-GAN, C-GAN, CDC-GAN, and AC- GAN) were employed to expand a reduced EuroSat dataset by 50%. The augmented datasets were subsequently used to train Convolutional Neural Networks (CNNs) for image classification. Comprehensive evaluation metrics (accuracy, recall, precision, Fl-score, AUC, IS, and FID) were employed to assess the performance of the generated images and the trained models. Results indicate that CDC-GAN exhibited the highest classification accuracy and MCC, while AC-GAN excelled in ROC-AUC, precision, and recall. This study underscores the potential of GAN s as a valuable tool for enhancing remote sensing image datasets and improving classification performance. © 2024 IEEE.

关键词： Gallium nitride

来源：评论

学校读者我要写书评

暂无评论

Multi-Robot Privacy-Preserving Algorithms Based on Federated Learning:A Review

引用

Computers, Materials & Continua 2023年第12期77卷 2971-2994页

作者： Jiansheng Peng Jinsong Guo Fengbo Bao Chengjun Yang Yong Xu Yong Qin College of Automation Guangxi University of Science and TechnologyLiuzhou545000China Department of Artificial Intelligence and Manufacturing Hechi UniversityHechi547000China

The robotics industry has seen rapid development in recent years due to the Corona Virus Disease *** the development of sensors and smart devices,factories and enterprises have accumulated a large amount of data in their daily production,which creates extremely favorable conditions for robots to perform machine ***,in recent years,people’s awareness of data privacy has been increasing,leading to the inability to circulate data between different enterprises,resulting in the emergence of data *** emergence of federated learning provides a feasible solution to this problem,and the combination of federated learning and multi-robot systems can break down data silos and improve the overall performance of ***,as scholars have studied more deeply,they found that federated learning has very limited privacy ***,how to protect data privacy from infringement remains an important *** this paper,we first give a brief introduction to the current development of multi-robot and federated learning;second,we review three aspects of privacy protection methods commonly used,privacy protection methods for multi-robot,and Other Problems Faced by Multi-robot Systems,focusing on method comparisons and challenges;and finally draw conclusions and predict possible future research directions.

关键词： Federated learning multi-robot privacy protection gradient leakage attacks

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Road Scene Semantic Segmentation Algorithm

引用

Computers, Materials & Continua 2023年第11期77卷 1929-1948页

作者： Jiansheng Peng Qing Yang Yaru Hou College of Automation Guangxi University of Science and TechnologyLiuzhou545000China Department of Artificial Intelligence and Manufacturing Hechi UniversityHechi547000China

In recent years,with the continuous deepening of smart city construction,there have been significant changes and improvements in the field of intelligent *** semantic segmentation of road scenes has important practical significance in the fields of automatic driving,transportation planning,and intelligent transportation ***,the current mainstream lightweight semantic segmentation models in road scene segmentation face problems such as poor segmentation performance of small targets and insufficient refinement of segmentation ***,this article proposes a lightweight semantic segmentation model based on the LiteSeg model improvement to address these *** model uses the lightweight backbone network MobileNet instead of the LiteSeg backbone network to reduce the network parameters and computation,and combines the Coordinate Attention(CA)mechanism to help the network capture long-distance *** the same time,by combining the dependencies of spatial information and channel information,the Spatial and Channel Network(SCNet)attention mechanism is proposed to improve the feature extraction ability of the ***,a multiscale transposed attention encoding(MTAE)module was proposed to obtain features of different resolutions and perform feature *** this paper,the proposed model is verified on the Cityscapes *** experimental results show that the addition of SCNet and MTAE modules increases the mean Intersection over Union(mIoU)of the original LiteSeg model by 4.69%.On this basis,the backbone network is replaced with MobileNet,and the CA model is added at the same *** the cost of increasing the minimum model parameters and computing costs,the mIoU of the original LiteSeg model is increased by 2.46%.This article also compares the proposed model with some current lightweight semantic segmentation models,and experiments show that the comprehensive performance of the proposed model is the best,especially in

关键词： Semantic segmentation lightweight road scenes multi-scale transposition attention encoding(MTAE)

来源：评论

学校读者我要写书评

暂无评论

Dream to Drive With Predictive Individual World Model

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-16页

作者： Gao, Yinfeng Zhang, Qichao Ding, Da-Wei Zhao, Dongbin School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China

It is still a challenging topic to make reactive driving behaviors in complex urban environments as road users' intentions are unknown. Model-based reinforcement learning (MBRL) offers great potential to learn a reactive policy by constructing a world model that can provide informative states and imagination training. However, a critical limitation in relevant research lies in the scene-level reconstruction representation learning, which may overlook key interactive vehicles and hardly model the interactive features among vehicles and their long-term intentions. Therefore, this paper presents a novel MBRL method with a predictive individual world model (PIWM) for autonomous driving. PIWM describes the driving environment from an individual-level perspective and captures vehicles' interactive relations and their intentions via trajectory prediction task. Meanwhile, a behavior policy is learned jointly with PIWM. It is trained in PIWM's imagination and effectively navigates in the urban driving scenes leveraging intention-aware latent states. The proposed method is trained and evaluated on simulation environments built upon real-world challenging interactive scenarios. Compared with popular model-free and state-of-the-art model-based reinforcement learning methods, experimental results show that the proposed method achieves the best performance in terms of safety and efficiency. IEEE

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

A Review on Web data Mining to Detect Online Spread of Terrorism Activity 2

A Review on Web Data Mining to Detect Online Spread of Terro...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Jha, Saurav Kumar Pacharaney, Utkarsha Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Maharashtra Wardha India Faculty of Engineering and Technology Department of Artificial Intelligence and Machine learning Maharashtra Wardha India

ISBN: (纸本)9798331505745

This research study outlines the significant contribution that web data mining can make in discovering and combating the dissemination of online terrorism. With terrorist groups using the internet more and more to deliver propaganda, recruit, and organize, there is a pressing need for efficient monitoring and analysis of web content. This article discusses different data mining methods that can be used to identify and study patterns suggestive of terrorist activity throughout networked digital environments. Specifically, the embedding of machine learning algorithms, i.e., Support Vector Machines (SVM), Random Forest and Gradient Boosting, is investigated with regard to its suitability to differentiate between benign and harmful online content. These algorithms can process large volumes of data, where features are extracted, including URL structures, domain ages, and keyword frequencies, to detect anticipate threats. According to the article, feature extraction plays a crucial role in improving detection system accuracy, enabling real-time surveillance of anomalous online activities. In addition, the review discusses the problems that researchers and law enforcement agencies have been encountering in using web data mining for counter-terrorism purposes. Ethical concerns around privacy and civil liberties are addressed and technical challenges, including the quality of data and the dynamic character of online content, are elaborated. Scenarios in which false positives arising in detection systems may occur are also considered, with emphasis on the need for ongoing algorithm and technique refinement. © 2025 IEEE.

关键词： Crop protection

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis on Real-Time Twitter data Using LSTM with Mutually Inclusive Classifiers 8th

Sentiment Analysis on Real-Time Twitter Data Using LSTM with...

引用

8th International Conference on Information and Communication technology for Competitive Strategies, ICTCS 2023

作者： Soumya, B.J. Swetha, B.N. Meeradevi, Ak. Kanavalli, Anita Shubhangi Singh, Yashashwini Anuritha, L. Singh, Anushka Department of Artificial Intelligence and Data Science Ramaiah Institute of Technology Bengaluru India Department of Artificial Intelligence and Machine Learning Ramaiah Institute of Technology Bengaluru India

ISBN: (纸本)9789819707430

A novel approach to perform sentiment analysis on real-time Twitter data using long short-term memory (LSTM) neural networks with mutually inclusive classifiers. The work leverages the vast amount of publicly available Twitter data, enabling us to analyze the sentiments expressed by users in real-time. The Twitter data by cleaning, tokenizing, and removing stop words to create a high-quality dataset is being preprocessed. The preprocessed data is then fed into the LSTM neural network, which is known for its ability to model long-term dependencies in sequential data. To enhance the sentiment analysis performance, a mutually inclusive classifier framework is proposed. Traditional sentiment analysis models often categorize sentiments into distinct classes, such as positive and negative. In contrast, our mutually inclusive classifiers allow for multiple sentiments to be assigned to a single tweet. This approach is better suited to capture the nuances and complexities of human emotions often expressed on social media platforms like Twitter. The LSTM model with mutually inclusive classifiers using Python and popular deep learning libraries like TensorFlow and Keras is implemented. The model is trained on a labeled dataset, and hyperparameters are tuned to optimize its performance. To evaluate the effectiveness of the approach it uses various metrics, such as accuracy, precision, recall, and F1-score. In the experimental analysis, demonstrated the LSTM-based sentiment analysis model with mutually inclusive classifiers outperforms traditional sentiment analysis models. The findings contribute to the advancement of sentiment analysis techniques and offer valuable applications in understanding and analyzing user sentiments in the dynamic world of social media. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A Novel Dynamic Peer-to-Peer Carbon Right Sharing Scheme for Microgrid Clusters

引用

IEEE Transactions on Smart Grid 2025年第4期16卷 3226-3238页

作者： Zhou, Wei Lai, Jingang Li, Xi Zeng, Zhigang School of Artificial Intelligence and Automation China Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control Education Ministry of China Wuhan430074 China

In this paper, a novel four-level distributed game decision-making framework of dynamic peer-to-peer (P2P) carbon emission right (CER) sharing is proposed for microgrid clusters (MGCs), which consists of four phases: exploration, selection, equilibrium and correction. Firstly, in the exploration stage, the tradable information is published by microgrids (MGs) and an initial set of tradable options is constructed. Secondly, in the selection stage, bilateral transaction coefficients are calculated according to the deficit and surplus of CERs in the P2P carbon market, and then an optimal sharing matching scheme of CERs is designed to reduce invalid transactions. Thirdly, in the equilibrium stage, a P2P carbon right sharing strategy based on the Stackelberg game is proposed to realize the dynamic change in carbon prices and the flexible conversion of master-slave roles in P2P carbon trading, which can promote the popularity of carbon market. Fourthly, in the correction stage, a carbon emission right balancer (CERB) is developed to avoid the imbalance of CERs, and then a billing scheme including incentives and penalties is established to achieve the benefit redistribution after P2P carbon trading. In the end, numerical results illustrate the effectiveness of the proposed multi-layer game decision-making framework for P2P carbon right sharing among MGs. © 2010-2012 IEEE.

关键词： Carbon dioxide Emissions trading Carbon Peer-to-peer computing Carbon tax Microgrids Games Supply and demand Main-secondary Privacy

来源：评论

学校读者我要写书评

暂无评论

Visual SLAM Based on Object Detection Network:A Review

引用

Computers, Materials & Continua 2023年第12期77卷 3209-3236页

作者： Jiansheng Peng Dunhua Chen Qing Yang Chengjun Yang Yong Xu Yong Qin College of Automation Guangxi University of Science and TechnologyLiuzhou545000China Department of Artificial Intelligence and Manufacturing Hechi UniversityHechi547000China

Visual simultaneous localization and mapping(SLAM)is crucial in robotics and autonomous ***,traditional visual SLAM faces challenges in dynamic *** address this issue,researchers have proposed semantic SLAM,which combines object detection,semantic segmentation,instance segmentation,and visual *** the growing body of literature on semantic SLAM,there is currently a lack of comprehensive research on the integration of object detection and visual ***,this study aims to gather information from multiple databases and review relevant literature using specific *** focuses on visual SLAM based on object detection,covering different ***,it discusses the current research status and challenges in this field,highlighting methods for incorporating semantic information from object detection networks into mileage measurement,closed-loop detection,and map *** also compares the characteristics and performance of various visual SLAM object detection ***,it provides an outlook on future research directions and emerging trends in visual *** has shown that visual SLAM based on object detection has significant improvements compared to traditional SLAM in dynamic point removal,data association,point cloud segmentation,and other *** can improve the robustness and accuracy of the entire SLAM system and can run in real *** the continuous optimization of algorithms and the improvement of hardware level,object visual SLAM has great potential for development.

关键词： Object detection visual SLAM visual odometry loop closure detection semantic map

来源：评论

学校读者我要写书评

暂无评论

Fossil-Net Lung Cancer Prediction and Classification from CT Images Using Convolution Neural Networks 2

Fossil-Net Lung Cancer Prediction and Classification from CT...

引用

2nd International Conference on Computing and data Analytics, ICCDA 2024

作者： Deepa, V. Merlin Christo, F. Rajalakshmi Institute of Science and Technology Department of Artificial Intelligence and Data Science TamilNadu Chennai600124 India

ISBN: (纸本)9798331542573

Lung cancer is the leading cause of death worldwide for both men and women. The most well-known disease is the heart disease followed by lung cancer. Early discovery of lung cancer can effectively treat lung cancer at an early stage. The potential for an early diagnosis of lung cancer to increase a patient's chance of survival. goal of this work was to identify lung malignancies in their early stages using supervised Learning. The Random forest model outperforms all other supervised machine learning methods for the Prediction of Lung cancer. The Objective of this study is to compare the different types of the machine Learning algorithms and provide the better Accuracy. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

A new adaptive gradient method with gradient decomposition

引用

Machine Learning 2025年第7期114卷 1-24页

作者： Shao, Zhou Zhou, Hang Lin, Tong Center for Data Science Peking University Beijing100871 China School of Mathematical Science Peking University Beijing100871 China State Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University Beijing100871 China

Abstract: Adaptive gradient methods, especially Adam-type methods (such as Adam, AMSGrad, and AdaBound), have been proposed to speed up the training process with an element-wise scaling term on learning rates. However, they often generalize poorly compared with stochastic gradient descent (SGD) and its accelerated schemes such as SGD with momentum (SGDM). In this paper, we propose a new adaptive method called DecGD, which aims at achieving both good generalization like SGDM and rapid convergence like Adam-type methods. In particular, DecGD decomposes the current gradient into the product of two terms including a surrogate gradient and a loss vector. Our method adjusts the learning rates adaptively according to the current loss vector instead of the squared gradients used in Adam-type methods. The intuition for adaptive learning rates of DecGD is that a good optimizer needs to decrease the learning rates as the loss decreases, which is similar to the learning rates decay scheduling technique. Therefore, DecGD gets a rapid convergence by enabling learning rate decay in accordance with the loss vector. Convergence analysis is discussed in both convex and non-convex situations. Finally, empirical results on widely-used tasks demonstrate that DecGD shows better generalization performance than SGDM and offers the same rapid convergence as Adam-type methods. © The Author(s), under exclusive licence to Springer science+Business Media LLC, part of Springer Nature 2025.

关键词： Adam-type methods Gradient decomposition Optimizer

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：