检索结果-内蒙古大学图书馆

Sustainable Communication Networks and Application (ICSCNA), International Conference on

作者： A. Syed Ismail S. Nikkath Bushra Department of Data Science and Business System Department of Computing Technologies SRM Institute of Science and Technology SRM Nagar Kattankulathur

Analyzing sentiment in micro-blogs, such as tweets or short social media posts, is a challenging yet important task in natural language processing (NLP). Deep learning techniques have shown great promise in this domain. Here's a novel approach for sentimental analysis using a deep neural network for micro-blogs. With the exponential growth of user-generated content on online platforms, YouTube has emerged as a dominant space for both creators and viewers to interact. One crucial aspect of this interaction is the comment section, where viewers express their thoughts and sentiments. This research presents a robust sentiment analysis model tailored specifically for YouTube video comments, aiming to extract valuable insights from this rich source of user-generated content. Ultimately, our novel deep neural network approach for micro-blog sentiment analysis demonstrates promising results, offering valuable insights into public sentiment across various social media platforms Using a deep neural network, this study presents a sentiment analysis model for YouTube video comments. This research contributes to the advancement of sentiment analysis methodologies, addressing the unique challenges posed by the concise and informal nature of micro-blogs. Our method, a mathematical model, and individuals were utilized to categorize the comments on various blogs. It was assumed that the classification of humans was entirely accurate. The results showed that, with classification accuracy ranging from 90% to 97%, our model is more precise than the numerical model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of CNN and SVM Machine Learning Techniques for Plant Disease Detection 4th

Comparative Analysis of CNN and SVM Machine Learning Techniq...

引用

4th International Conference on data, Engineering, and Applications, IDEA 2022

作者： Adeniyi, Abidemi Emmanuel Madamidola, Olugbenga Ayomide Awotunde, Joseph Bamidele Misra, Sanjay Agrawal, Akshat Department of Computer Science College of Computing and Communication Studies Bowen University Iwo Nigeria Department of Information Technology Federal University of Technology Akure Nigeria Department of Computer Science Faculty of Communication and Information Sciences University of Ilorin Ilorin Nigeria Department of Applied Data Science Institute for Energy Technology Halden Norway Department of Computer Science & Engineering Amity University Haryana Gurugram122412 India

ISBN: (纸本)9789819700363

The growing advancement of different jobs, skills and businesses has stimulated the spread of diseases. Most of the time, these diseases can cross countries’ borders and spread at a very rapid rate. Avoiding and detecting these infections have proved to be a major problem for our public health and one that must be treated with great importance. Crop disease has haunted, farmers have been victimized for several decades, and a remedy must be offered to halt this damage. As a result, a system should be developed to detect plant disease. Untreated plant diseases ultimately result in a loss to the farmer. Traditional methods of detecting plant disease have become less efficient and inaccurate;thus there is need to improve on the techniques of plant disease detection, as a reliable detection of plant diseases will greatly improve the quality of food crops produced and decrease the threat plant diseases pose to food security. Therefore, this study is aimed at analyzing comparatively, two machine learning language techniques convolutional neural network (CNN) and support vector machine (SVM) in terms of their respective accuracy in detecting plant diseases through their leaves in which both algorithms are used for the automatic diagnosis of plant disease. From the experimental test conducted on various plants using CNN and SVM algorithms, CNN had an accuracy of 98%, while SVM had an accuracy of 62% on various plant leaves used. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Meta-CQG: A Meta-Learning Framework for Complex Question Generation over Knowledge Bases 29

Meta-CQG: A Meta-Learning Framework for Complex Question Gen...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Zhang, Kun Qiu, Yunqi Wang, Yuanzhuo Bai, Long Li, Wei Jiang, Xuhui Shen, Huawei Cheng, Xueqi Data Intelligence System Research Center Institute of Computing Technology Chinese Academy of Sciences China School of Computer Science and Technology University of Chinese Academy of Sciences China Big Data Academy Zhongke Baidu Inc

Complex question generation over knowledge bases (KB) aims to generate natural language questions involving multiple KB relations or functional constraints. Existing methods train one encoder-decoder-based model to fit all questions. However, such a one-size-fits-all strategy may not perform well since complex questions exhibit an uneven distribution in many dimensions, such as question types, involved KB relations, and query structures, resulting in insufficient learning for long-tailed samples under different dimensions. To address this problem, we propose a meta-learning framework for complex question generation. The meta-trained generator can acquire universal and transferable meta-knowledge and quickly adapt to long-tailed samples through a few most related training samples. To retrieve similar samples for each input query, we design a self-supervised graph retriever to learn distributed representations for samples, and contrastive learning is leveraged to improve the learned representations. We conduct experiments on both WebQuestionsSP and Com-plexWebQuestion, and results on long-tailed samples of different dimensions have been significantly improved, which demonstrates the effectiveness of the proposed framework. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Cognitive Farming in Agriculture: Deploying CNN-RF for Maize Disease Precision Diagnostics 2

Cognitive Farming in Agriculture: Deploying CNN-RF for Maize...

引用

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

作者： Nisha Chandran, S. Garg, Ashish Namdev, Dheeraj Kukreja, Vinay Mehta, Shiva School of Computing Graphic Era Hill University Uttarakhand Dehradun India Graphic Era Deemed to be University Computer Science and Engineering Uttarakhand Dehradun India IIMT College of Engineering Artificial Intelligence & Data Science Uttar Pradesh Greater Noida201310 India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

ISBN: (纸本)9798350383652

A hybrid approach integrating both CNN and RF is investigated in this research study of the Survey regarding the classification of maize leaf diseases with the help of CNN and RF. Our research carefully contrasts five created disease severities as a reported diagnostic tool for agriculturalists. The high accuracy of the model was extensively validated by applying various performance metrics with excellent precision of the different classes ranging from 95.90% to 98.47% for recall ranged between 95.01% to 99.21%, and F1- scores ranged between 96.55% to 98.4. The model achieved a general accuracy of 97.42851 %. We employed various averaging approaches to generalize the performance results across varying illness levels. A macro average yielded an accuracy of 97.37%, recall of 97.48%, and F1-score of 97.42%, implying similarity of performance across classes. Considering class imbalance, the weighted average was accurate at 97.44%, recalled at 97.43%, and the F1-score was similar at 97.43%. The micro average, as the aggregation of results across classes, was remarkably stable at 97.43 %, representing the performance of the model well and especially favoring frequent courses. Early identification and classification of diseases affecting maize leaves significantly contributed to precision agriculture, and this paper presents a reliable and efficient method for a timely diagnosis. It shows the stable performance of the CNN-RF model because many statistical measures are indicated. This implies that it possesses reasonable practicality in agricultural applications that highly support pest control and increase crop yields. © 2024 IEEE.

关键词： Agriculture Convolutional neural networks (CNNs) Image classification Maize Leaf Diseases Random Forest

来源：评论

学校读者我要写书评

暂无评论

Cyber Security Issues and Challenges Related to Generative AI and ChatGPT

Cyber Security Issues and Challenges Related to Generative A...

引用

International Conference on Social Networks Analysis, Management and Security (SNAMS)

作者： Rajesh Pasupuleti Ravi Vadapalli Christopher Mader Frost Institute for Data Science and Computing (IDSC) University of Miami Coral Gables FL USA IDSC Advanced Computing Systems Electrical and Computer Engineering (ECE) University of Miami Coral Gables FL USA Systems and Data Engineering Frost Institute for Data Science and Computing (IDSC) University of Miami Coral Gables FL USA

In recent years, Generative Artificial Intelligence (AI) and ChatGPT (Generative Pre-trained Transformer) models that are capable of generating realistic human-mimicked languages have gained progressive popularity. With the evolution of technology, there has been a significant increase in the availability and usage of artificial intelligence tools, such as ChatGPT and Generative AI, that will assist in shaping the future. However, this increasing popularity poses a potential risk if used inappropriately. Threats from AI pose special challenges for government, the private sector, and national security. In this paper, we address some of key concerns of significant cyber security issues and challenges related to Generative AI and ChatGPT. With careful consideration to application usage, organizations can implement appropriate security measures to mitigate these risks. We also incorporate recommendations about ChatGPT usage and its impact on society. It is important that researchers, developers, and policymakers (CIOs, CSOs) work together to mitigate these risks and to ensure that these models are used in a responsible and ethical manner.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Robust Universal Information Extraction: Benchmark, Evaluation, and Solution

arXiv

引用

arXiv 2025年

作者： Zhu, Jizhao Shi, Akang Li, Zixuan Bai, Long Jin, Xiaolong Guo, Jiafeng Cheng, Xueqi Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China School of Computer Science Shenyang Aerospace University Shenyang China

In this paper, we aim to enhance the robustness of Universal Information Extraction (UIE) by introducing a new benchmark dataset, a comprehensive evaluation, and a feasible solution. Existing robust benchmark datasets have two key limitations: 1) They generate only a limited range of perturbations for a single Information Extraction (IE) task, which fails to evaluate the robustness of UIE models effectively;2) They rely on small models or handcrafted rules to generate perturbations, often resulting in unnatural adversarial examples. Considering the powerful generation capabilities of Large Language Models (LLMs), we introduce a new benchmark dataset for Robust UIE, called RUIE-Bench, which utilizes LLMs to generate more diverse and realistic perturbations across different IE tasks. Based on this dataset, we comprehensively evaluate existing UIE models and reveal that both LLM-based models and other models suffer from significant performance drops. To improve robustness and reduce training costs, we propose a data-augmentation solution that dynamically selects hard samples for iterative training based on the model’s inference loss. Experimental results show that training with only 15% of the data leads to an average 7.5% relative performance improvement across three IE tasks. Copyright © 2025, The Authors. All rights reserved.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

LithoHoD: A Litho Simulator-Powered Framework for IC Layout Hotspot Detection

引用

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 2025年第3期44卷 1098-1111页

作者： Shao, Hao-Chiang Chen, Guan-Yu Lin, Yu-Hsien Lin, Chia-Wen Fang, Shao-Yun Tsai, Pin-Yian Liu, Yan-Hsiu National Chung Hsing University Institute of Data Science and Information Computing Taichung402202 Taiwan Novatek Microelectronics Corporation Hsinchu300092 Taiwan National Tsing Hua University Department of Electrical Engineering Hsinchu300044 Taiwan National Tsing Hua University Department of Electrical Engineering The Institute of Communications Engineering Hsinchu300044 Taiwan National Taiwan University of Science and Technology Department of Electrical Engineering Taipei106335 Taiwan United Microelectronics Corporation Product Engineering Department Hsinchu300094 Taiwan United Microelectronics Corporation Development of Smart Manufacturing Hsinchu300094 Taiwan

Recent advances in VLSI fabrication technology have led to die shrinkage and increased layout density, creating an urgent demand for advanced hotspot detection techniques. However, by taking an object detection network as the backbone, recent learning-based hotspot detectors learn to recognize only the problematic layout patterns in the training data. This fact makes these hotspot detectors difficult to generalize to real-world scenarios. We propose a novel lithography simulator-powered hotspot detection framework to overcome this difficulty. Our framework integrates a lithography simulator with an object detection backbone, merging the extracted latent features from both the simulator and the object detector via well-designed cross-attention blocks. Consequently, the proposed framework can be used to detect potential hotspot regions based on 1) the variation of possible circuit shape deformation estimated by the lithography simulator and 2) the problematic layout patterns already known. To this end, we utilize RetinaNet with a feature pyramid network as the object detection backbone and leverage LithoNet as the lithography simulator. Extensive experiments demonstrate that our proposed simulator-guided hotspot detection framework outperforms the previous state-of-the-art methods on real-world data. © 2024 IEEE.

关键词： Integrated circuit layout

来源：评论

学校读者我要写书评

暂无评论

FocusDD: Real-World Scene Infusion for Robust dataset Distillation

arXiv

引用

arXiv 2025年

作者： Hu, Youbing Cheng, Yun Saukh, Olga Ozdemir, Firat Lu, Anqi Cao, Zhiqiang Li, Zhijun Faculty of Computing Harbin Institute of Technology China Swiss Data Science Center Zurich Switzerland Graz University of Technology Austria Complexity Science Hub Vienna Austria

dataset distillation has emerged as a strategy to compress real-world datasets for efficient training. However, it struggles with large-scale and high-resolution datasets, limiting its practicality. This paper introduces a novel resolution-independent dataset distillation method Focused dataset Distillation (FocusDD), which achieves diversity and realism in distilled data by identifying key information patches, thereby ensuring the generalization capability of the distilled dataset across different network architectures. Specifically, FocusDD leverages a pre-trained Vision Transformer (ViT) to extract key image patches, which are then synthesized into a single distilled image. These distilled images, which capture multiple targets, are suitable not only for classification tasks but also for dense tasks such as object detection. To further improve the generalization of the distilled dataset, each synthesized image is augmented with a downsampled view of the original image. Experimental results on the ImageNet-1K dataset demonstrate that, with 100 images per class (IPC), ResNet50 and MobileNet-v2 achieve validation accuracies of 71.0% and 62.6%, respectively, outperforming state-of-the-art methods by 2.8% and 4.7%. Notably, FocusDD is the first method to use distilled datasets for object detection tasks. On the COCO2017 dataset, with an IPC of 50, YOLOv11n and YOLOv11s achieve 24.4% and 32.1% mAP, respectively, further validating the effectiveness of our approach. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generative AI: A Review on Models and Applications 2

Generative AI: A Review on Models and Applications

引用

2nd IEEE International Conference on Communication, Security and Artificial Intelligence, ICCSAI 2023

作者： Kaswan, Kuldeep Singh Dhatterwal, Jagjit Singh Malik, Kiran Baliyan, Anupam School of Computing Science and Engineering Galgotias University UP Greater Noida India Koneru Lakshmaiah Education Foundation Artificial Intelligence and Data Science AP Guntur India Matu Ram Institute of Engineering and Management Computer Science and Engineering Haryana Rohtak India Chandigarh University Department of Computer Science and Engineering Chandigarh India

ISBN: (纸本)9798350369960

Generative Artificial Intelligence (AI) stands as a transformative paradigm in machine learning, enabling the creation of complex and realistic data from latent representations. This review paper comprehensively surveys the landscape of Generative AI, encompassing its foundational concepts, diverse models, training methodologies, applications, challenges, recent advancements, evaluation metrics, and ethical dimensions. The paper begins by introducing Generative AI's significance across various domains, presenting its pivotal role in producing synthetic data with applications spanning image synthesis, text generation, music composition, drug discovery, and more. The objectives lie in elucidating the foundational concepts, delving into model intricacies, unveiling the training procedures, exploring its application landscape, addressing challenges, envisioning future directions, and discussing ethical ramifications. The foundational section elucidates the diverse array of generative models, including Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), flow-based models, Generative Reinforcement Learning (GRL), and advanced hybrid architectures. Subsequently, evaluation metrics ranging from Inception Score to perceptual similarity metrics and human evaluations are surveyed to assess generative model performance. Finally, ethical considerations underscore the necessity for addressing biases, misuse, intellectual property concerns, and the call for responsible AI development and regulation in the Generative AI landscape. © 2023 IEEE.

关键词： Advanced Hybrid Architectures Flow-Based Models Generative Adversarial Networks (GANs) Generative Reinforcement Learning (GRL) Variational Autoencoders (VAEs)

来源：评论

学校读者我要写书评

暂无评论

Cloud-Based Road Safety for Real-Time Vehicle Rash Driving Alerts with Random Forest Algorithm 3

Cloud-Based Road Safety for Real-Time Vehicle Rash Driving A...

引用

3rd International Conference for Innovation in Technology, INOCON 2024

作者： Presitha Aarthi, M. Reddy, Chilukala Mahender Anbarasi, A. Mohankumar, N. Ishwarya, M.V. Murugan, S. Shree Sathyam College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Salem India Gitam University Department of Computer Science and Engineering Telangana Hyderabad India Srm Institute of Science and Technology School of Computing Department of Computing Technologies Chennai Tamil Nadu Kattankulathur India B.V. Raju Institute of Technology Department of Electronics and Communication Engineering Telangana Hyderabad India Agni College of Technology Artificial Intelligence and Data Science Department Tamil Nadu Chennai India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Biomedical Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350381931

The cloud-based road safety technology introduced in this research improves real-time vehicle behavior monitoring and warns for rash driving. It uses cloud computing to gather and interpret data from onboard car sensors and other traffic monitoring equipment. Powerful machine learning technology the Random Forest (RF) algorithm analyses this data intelligently. The RF algorithm is trained on a varied array of driving metrics to detect rash driving tendencies. Real-time data streams may be processed efficiently and scalable on the cloud, enabling speedy decision-making for rash driving detection. A network sends alerts to authorities and nearby vehicles. The system is adaptable to different road conditions, resistant to sensor data noise, and able to enhance rash driving detection accuracy via model updates. Cloud architecture makes the system available worldwide. With its focus on real-time notifications utilizing the RF algorithm, this cloud-based road safety system may reduce the hazards of reckless driving and avoid accidents. © 2024 IEEE.

关键词： Cloud computing architecture

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：