检索结果-内蒙古大学图书馆

Enhancing low-resource cross-lingual summarization from noisy data with fine-grained reinforcement learning

Frontiers of Information technology & Electronic engineering 2024年第1期25卷 121-134页

作者： Yuxin HUANG Huailing GU Zhengtao YU Yumeng GAO Tong PAN Jialong XU Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming 650504China Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and TechnologyKunming 650504China

Cross-lingual summarization(CLS)is the task of generating a summary in a target language from a document in a source ***,end-to-end CLS models have achieved impressive results using large-scale,high-quality datasets typically constructed by translating monolingual summary corpora into CLS ***,due to the limited performance of low-resource language translation models,translation noise can seriously degrade the performance of these *** this paper,we propose a fine-grained reinforcement learning approach to address low-resource CLS based on noisy *** introduce the source language summary as a gold signal to alleviate the impact of the translated noisy target ***,we design a reinforcement reward by calculating the word correlation and word missing degree between the source language summary and the generated target language summary,and combine it with cross-entropy loss to optimize the CLS *** validate the performance of our proposed model,we construct Chinese-Vietnamese and Vietnamese-Chinese CLS *** results show that our proposed model outperforms the baselines in terms of both the ROUGE score and BERTScore.

关键词： Cross-lingual summarization Low-resource language Noisy data Fine-grained reinforcement learning Word correlation Word missing degree

来源：评论

学校读者我要写书评

暂无评论

Automatic Fruit Detection Based on Robotic Vision 5

Automatic Fruit Detection Based on Robotic Vision

引用

5th International Conference on Big data and artificial intelligence and Software engineering, ICBASE 2024

作者： Chen, Yiran Yao, Rui Liu, Haoran Liu, Bingqi Liu, Mingzhe Wenzhou University of Technology School of Data Science and Artificial Intelligence Wenzhou China Chengdu University of Technology College of Nuclear Technology and Automation Engineering Chengdu China Norla Institute of Technical Physics Chengdu China

ISBN: (纸本)9798331506612

Automatic fruit detection has greatly reduced labor costs and crop damage rates, contributing to the progress of agricultural modernization. It involves real-time assessment of the surrounding environment and recognition of target fruit categories. However, fruit detection faces challenges due to the similarities in shape, color, and other features among different types of fruits, as well as the impact of environmental factors such as inadequate lighting, occlusion, and background variations on recognition accuracy. This project focuses on the simulation of the robotic fruit harvesting process, which includes environmental image acquisition, image processing, and robot control. The robot utilizes its integrated camera to capture real-time images of the surrounding environment. These images are then processed on a computer, employing color recognition based on traditional algorithms. The images are segmented based on the identified color regions and subjected to object detection using YOLO v5. By discerning the presence of the target objects, the results are transmitted to the robot, which responds accordingly. The real-time performance is enhanced by filtering and narrowing down the target regions, reducing the time required for object recognition. © 2024 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Personalized Method for Voting in Wireless Mobile Adhoc Networks with Intrusion Detection using NS2 Simulation Model 5

Personalized Method for Voting in Wireless Mobile Adhoc Netw...

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Muthukumar, S. Senthil Pandi, S. Menaga, D. Sudhahar, T.N. St.Joseph's Institute of Technology Department of Computer Science and Engineering Tamilnadu Chennai India Rajalakshmi Engineering College Department of Computer Science and Engineering Tamilnadu Chennai India Rajalakshmi Institute of Technology Department of Artificial Intelligence and Data Science Tamilnadu Chennai India

ISBN: (纸本)9798331504403

Mobile Ad hoc Networks (MANETs) are wireless networks that are self-configuring, infrastructure-less, and dynamic. The nodes in these networks have limited access to available resources. MANETs use intrusion detection systems, also known as IDS, to monitor activities in order to identify any potential intrusions into the network, which would otherwise be vulnerable. In this study, we offer efficient techniques for maximizing the length of time that intrusion detection systems need to be active in a mobile ad hoc network and monitoring how much time they need to be active for. The dissemination of a probabilistic model that makes use of neighborhood node IDS collaboration in order to reduce the amount of individual active time. In order to monitor network activities, an IDS often needs to be running nonstop on every node. In terms of electricity and processing resources, this could end up being a costly overhead for a mobile device that runs on batteries. We therefore want to shorten the IDSs' active time in this work without sacrificing their effectiveness. We simulate the interactions between IDSs as a multiplayer cooperative game with partially cooperative and partially opposing aims in order to validate our suggested methodology. We investigate this game theoretically and provide evidence from simulations. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Epilepsy Detection Using Supervised Learning Algorithms 2

Epilepsy Detection Using Supervised Learning Algorithms

引用

2nd IEEE International Conference on Contemporary Computing and Communications, InC4 2024

作者： Krishnasamy, Lalitha Sriwastav, Yash Kumar Bharat, Suchak Pratik Ganachar, Sanjana R Nandha Engineering College Department of Artificial Intelligence and Data Science Erode India School of Engineering and Technology Christ University Department of CSE Bengaluru India School of Engineering and Technology Christ University Department of CSE AIML Bengaluru India

ISBN: (纸本)9798350383652

In the current scenario, people are suffering and isolated by themselves by seizure detection and prediction in epilepsy. Also, it is highly essential that it needs to be identified through wearable devices. Researchers discussed this issue and outlined future developments in this field, suggesting that Machine Learning (ML) techniques could radically change how we diagnose and manage patients with epilepsy. However, as data availability has increased, Deep Learning (DL) techniques have become the most cutting-edge approach to adopt and use with wearable devices. On the other hand, large amounts of data are needed to train DL models, making overfitting problematic. DL models are created with open-source toolboxes and Python, allowing researchers to create automated systems and broaden computational accessibility. This work thoroughly overviews deep learning (DL) methods and neuroimaging modalities for automated epileptic seizure identification. It covers several MRI and EEG techniques for epileptic seizure diagnosis and treatment programmes designed to treat these seizures. The study also covers the difficulties in precise detection, the benefits and drawbacks of DL-based strategies, potential DL models and upcoming research in this area. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Imitation Learning from Purified Demonstrations 41

Imitation Learning from Purified Demonstrations

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wang, Yunke Dong, Minjing Zhao, Yukun Du, Bo Xu, Chang School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Wuhan Institute of Data Intelligence Wuhan University China Department of Computer Science City University of Hong Kong Hong Kong School of Computer Science Faculty of Engineering The University of Sydney Australia

Imitation learning has emerged as a promising approach for addressing sequential decision-making problems, with the assumption that expert demonstrations are optimal. However, in real-world scenarios, most demonstrations are often imperfect, leading to challenges in the effectiveness of imitation learning. While existing research has focused on optimizing with imperfect demonstrations, the training typically requires a certain proportion of optimal demonstrations to guarantee performance. To tackle these problems, we propose to purify the potential noises in imperfect demonstrations first, and subsequently conduct imitation learning from these purified demonstrations. Motivated by the success of diffusion model, we introduce a two-step purification via diffusion process. In the first step, we apply a forward diffusion process to smooth potential noises in imperfect demonstrations by introducing additional noise. Subsequently, a reverse generative process is utilized to recover the optimal demonstration from the diffused ones. We provide theoretical evidence supporting our approach, demonstrating that the distance between the purified and optimal demonstration can be bounded. Empirical results on MuJoCo and RoboSuite demonstrate the effectiveness of our method from different aspects. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Comparison Between ResNet 16 and Inception V4 Network for COVID-19 Prediction 7th

Comparison Between ResNet 16 and Inception V4 Network for CO...

引用

7th International Conference on Emerging Research in Computing, Information, Communication and Applications, ERCICA 2022

作者： Rachana, P.J. Kodipalli, Ashwini Rao, Trupthi Department of Mechanical Engineering National Institute of Technology Karnataka Karnataka Surathkal India Department of Artificial Intelligence and Data Science Global Academy of Technology Bangalore India

ISBN: (纸本)9789811954818

COVID-19 claimed 5 million lives worldwide so far, and the count is continuing. It also affected socio-economic life of almost everybody in the world. Due to COVID-19, mortality and morbidity are continuing, and it is necessary to find new methods and techniques to contain the infection. Every government is trying hard to implement a new strategy to minimize the spread of the virus. COVID-19 infection occurs due to the virus strain SARS-COV-2. Generally, death occurs due to COVID-19 because of suppurative pulmonary infection and subsequent septic shock or multiorgan failure. In the literature, there are some computational techniques which use deep learning models and reported fairly good performance. This paper proposes a new deep learning architecture inception v4 to automatically detect COVID-19 using the chart X-ray images. The proposed methodology provided improved performance of 98.7 and 94.8% of training and validation accuracy. The developed technology can be used to detect COVID-19 with a high performance;the same may be deployed by the various governments in the detection and the management of COVID-19 in an efficient manner. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

A deep neural network based surrogate model for damage identification in full-scale structures with incomplete noisy measurements

引用

Frontiers of Structural and Civil engineering 2024年第3期18卷 393-410页

作者： Tram BUI-NGOC Duy-Khuong LY Tam T TRUONG Chanachai THONGCHOM T.NGUYEN-THOI Laboratory for Computational Mechanics Institute for Computational Science and Artificial IntelligenceVan Lang UniversityHo Chi Minh City 70000Vietnam Faculty of Mechanical-Electrical and Computer Engineering School of TechnologyVan Lang UniversityHo Chi Minh City 70000Vietnam Faculty of Civil Engineering School of TechnologyVan Lang UniversityHo Chi Minh City 70000Vietnam Department of Computer Science Aarhus UniversityAarhus 8000Denmark Thammasat University research unit in structural and foundation engineering Department of Civil EngineeringThammasat UniversityPathumthani 12120Thailand Laboratory for Applied and Industrial Mathematics Institute for Computational Science and Artificial IntelligenceVan Lang UniversityHo Chi Minh City 70000Vietnam Thammasat School of Engineering Thammasat UniversityPathumthani 12120Thailand

The paper introduces a novel approach for detecting structural damage in full-scale structures using surrogate models generated from incomplete modal data and deep neural networks(DNNs).A significant challenge in this field is the limited availability of measurement data for full-scale structures,which is addressed in this paper by generating data sets using a reduced finite element(FE)model constructed by SAP2000 software and the MATLAB programming *** surrogate models are trained using response data obtained from the monitored structure through a limited number of measurement *** proposed approach involves training a single surrogate model that can quickly predict the location and severity of damage for all potential *** achieve the most generalized surrogate model,the study explores different types of layers and hyperparameters of the training algorithm and employs state-of-the-art techniques to avoid overfitting and to accelerate the training *** approach’s effectiveness,efficiency,and applicability are demonstrated by two numerical *** study also verifies the robustness of the proposed approach on data sets with sparse and noisy measured ***,the proposed approach is a promising alternative to traditional approaches that rely on FE model updating and optimization algorithms,which can be computationally *** approach also shows potential for broader applications in structural damage detection.

关键词： vibration-based damage detection deep neural network full-scale structures finite element model updating noisy incomplete modal data

来源：评论

学校读者我要写书评

暂无评论

artificial intelligence Cultivation: Transforming Agriculture for a Smart and Sustainable Future

Artificial Intelligence Cultivation: Transforming Agricultur...

引用

Intelligent data Communication Technologies and Internet of Things (IDCIoT), International Conference on

作者： Bhushan Fulkar Samir Mendhe Pawan Patil Department of Artificial Intelligence and Data science Faculty of Engineering and Technology DMIHER(DU) Wardha Maharashtra India Computer Science and Design Faculty of Engineering and Technology DMIHER(DU) Wardha Maharashtra India Artificial Intelligence and Data science Faculty of Engineering and Technology DMIHER(DU) Wardha Maharashtra India

The growing global population is posing unprecedented challenges for the agriculture industry, requiring it to produce more food while also addressing resource constraints and environmental concerns. artificial intelligence (AI) has changed the game in agriculture by offering creative solutions to increase productivity, optimize resource use, and promote sustainability. artificial intelligence (AI) has been used in the agriculture sector more and more recently. A few of the problems the industry faces in attempting to maximize its produce are improper soil treatment, disease and pest infestation, the use of driverless tractors, big data requirements, and the knowledge gap between farmers and technology. This work provides an overview of the applications of artificial intelligence in crop, weed, and disease management. The proposed work aims to review various AI techniques, including artificial neural networks (ANN) and fuzzy logic (FL).

关键词：

来源：评论

学校读者我要写书评

暂无评论

An improved energy management model for IoT devices using deep learning 15

An improved energy management model for IoT devices using de...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Reetha, P. Roy Sudha Joseph, S. Pandeeswari, N. Anitha, R. Juliyana, S. Jebarose PSNA College of Engineering and Technology Department of Artificial Intelligence and Data Science Tamil Nadu Dindigul Dt India Christian College of Engineering and Technology Department of Electronics and Communication Tamil Nadu Dindigul Dt India PSNA College of Engineering and Technology Department of Information Technology Tamil Nadu Dindigul Dt India Dr. Mahalingam college of engineering and Technology Department of Artificial intelligence and Data Science Tamil Nadu Pollachi India Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Department of Mechanical Engineering Tamil Ndu Chennai India

ISBN: (纸本)9798350370249

The Internet of Things (IoT) is booming, with research showing that billions of connected devices gather data, communicate, and automate. The widespread adoption of IoT devices has been hampered by one major challenge: limited energy resources that require recharging or replacing often. Energy management strategies on these devices are essential to improve battery life. This paper presents an enhanced version of the energy management model for IoT devices using deep learning techniques in technical abstracts. The aim is to reduce energy consumption by predicting and configuring real-time device settings based on user behavior trends. A deep neural network is used as the model to learn and tailor its response variably based on different user conditions like temperature, light, and usage patterns. The model can analyze this data to predict energy demand and programmatically adjust device settings. © 2024 IEEE.

关键词： Analyze Automate Energy Resources RealTime Widespread

来源：评论

学校读者我要写书评

暂无评论

Necessity of Information Security in Safeguarding Smart Grid Infrastructure 5

Necessity of Information Security in Safeguarding Smart Grid...

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Joshi, Namra Khandelwal, Achala Joshi, Shubham SVKM's Institute of Technology Department of Electrical Engineering Maharashtra Dhule India Thakur College of Engineering & Technology Kandivali Mumbai India Vishwakarma Institute of Information Technology Dept. of Artificial Intelligence & Data Science Pune India

ISBN: (纸本)9798331504403

The Indian economy is continuously growing, so the power demand is increasing abruptly. The power extraction from non-conventional energy sources has also increased in the past 10 years. Somehow generation and demand are matched. However, a competent infrastructure is needed to handle power generated from multiple sources. Smart Grid Systems has excellent properties to handle such situations in power systems. The highlights of the fundamentals of smart grid, recent developments in Smart Grid as well as Importance of Information Security in Smart Grid is discussed. © 2024 IEEE.

关键词： Power grids

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：