检索结果-内蒙古大学图书馆

3rd International Conference on Communication, Computing and Digital Systems, C-CODE 2023

作者： Rahman, Kiramat Ghani, Anwar Ahmad, Rashid Sajjad, Syed Haseeb International Islamic University Dept. of Software Engineering Islamabad Pakistan Big Data Research Center Jeju National University Jeju Korea Republic of Inernational Islamic University Dept. of Computer Science Islamabad Pakistan

ISBN: (纸本)9798350332391

This paper explores the concept of algorithmic hybridization, which involves combining various machine learning (ML) algorithms to enhance performance by utilizing the benefits of both simultaneously. This study presents a framework that utilizes a combination of long short-term memory (LSTM) and bidirectional LSTM (BiLSTM) with artificial neural networks (ANN) to classify non-functional requirements (NFR). The task of NFR classification is challenging due to the scarcity of supervised learning data. The effectiveness of the proposed approach was assessed by comparing the performance of our integrated model with that of single LSTM and BiLSTM models. To conduct this evaluation, we combined two datasets consisting of 1000 non-functional requirements (NFR). The experimental findings revealed that the proposed approach is effective as the hybrid models exhibited better precision, recall, and F-1 score compared to its counterparts. © 2023 IEEE.

关键词： Requirements engineering

来源：评论

学校读者我要写书评

暂无评论

Advanced Machine Learning Approaches to Combat Fake News in the Digital Era 4

Advanced Machine Learning Approaches to Combat Fake News in ...

引用

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

作者： Kaur, Tejinder Kumar Gantayat, Pradosh Das, Swatismita Majhi, Madhusmita Dept. of Mmictbm Mullana Haryana Ambala133207 India Department of Artificial Intelligence and Data Science Telangana Hyderabad501203 India Raajdhani Engineering College Bhubaneswar India Department of Computer Science and Engineering Telangana Hyderabad501203 India

ISBN: (纸本)9798350387490

This paper aims to provide the sustainable design for the user to provide them with ability to check whether the information is fake or real by providing the accuracy of the news using Machine learning via various algorithms with the help of database, which will respond as whether the news is accurate or not. Fake news has become a prevalent issue in today's digital age, causing significant societal impacts by spreading misinformation. This paper explores the application of machine learning techniques for detecting fake news. The paper also addresses challenges such as data scarcity, model interpretability, and the dynamic nature of fake news. We conclude with recommendations for future research directions, emphasizing the need for real-time detection systems and cross-disciplinary collaboration to enhance the effectiveness of fake news detection using machine learning. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Smart Intelligent Detecting and Alerting System for Industrial Gas Leakage using IoT in Sensor Network 5

An Enhanced Smart Intelligent Detecting and Alerting System ...

引用

5th International Conference on Smart Systems and Inventive Technology, ICSSIT 2023

作者： Senthil, G.A. Suganthi, P. Prabha, R. Madhumathi, M. Prabhu, S. Sridevi, S. Agni College of Technology Dept. of Information Technology Chennai India Sri Sai Ram Institute of Technology Dept. of Electronics and Communication Engineering Chennai India Karpaga Vinayaga College of Engineering and Technology Dept. of Artificial Intelligence and Data Science Chennai India Sri Ramachandra Engineering and Technology Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9781665474672

Leakage of any type of gas has emerged as a hazard in recent years, whether in a typical workplace, boiler, a commercial setting, a café, or a canteen, industries natural gas, coal, refinery products, crude oil, cement, electricity, steel, and fertilizers etc. In this article, I proposed a new invention of an IoT-based gas waste monitoring, leak detection, and alerting system. The research extends on the development of such an intelligent system that can intelligently preserve gas, ensure the safety precaution and pre vent accidents. The technique must be connected to the stove. The design incorporates ultrasonic sensors which identify bio gas leakage in circumstance with in square metre is usage area of industries or cooking place. The Proposed work smart intelligence system is cuts off the gas supply using an automated shutting off device. Whenever a gas leak is detected, consumers will be notified through SMS via GSM, location using GPRS, and will be able to resolve the situation as quickly as feasible. The flame sensor in the technology will supervise flame and fire. The buzzer starts to sound when a fire is detected. Aside from that, the system may save data on the cloud. With the help of this cloud storage solution, every user's daily gas use may be traced. Finally, this approach will aid in recognizing per user natural gas consumption. The system has been examined and is capable of monitoring gas loss, evacuation, and sending an SMS notification and location aid to the user. The precipitate demonstrated its usefulness in conserving a considerable amount of domestically squandered gas. © 2023 IEEE.

关键词： Liquefied petroleum gas

来源：评论

学校读者我要写书评

暂无评论

Enhancing Human Safety Through IoT-Integrated Smart Helmet Technology

Enhancing Human Safety Through IoT-Integrated Smart Helmet T...

引用

Expert Clouds and Applications (ICOECA), International Conference on

作者： Venkatesh K Harshitha Jodu Sree Kanthi P Yatheesh Kumar Reddy K Sumalatha R Dept. Computer Science and Engineering (Data Science) Srinivasa Ramanujan Institute of Technology Anantapur India

ISBN: (数字)9798350385793

ISBN: (纸本)9798350385809

The smart helmet's characteristics are meant to identify and report whether or not a wearer has consumed alcohol while donning a helmet. Road accidents are increasing as a result of riders drinking alcohol and not wearing helmets. In the modern world, thousands of people lose their lives in auto accidents each year. Wearing a smart helmet can typically lower the number of accidents. The primary objective of this research study is to create a wearable helmet that can both detect alcohol and prevent accidents without the need for a helmet. Whether the user is wearing a helmet is determined by the limit switch. The rider's breath is tested by the Gas sensor to determine whether alcohol is present. If the rider has ingested alcohol or is not wearing a helmet, the bike will not start. Only when a helmet is on and there are no indications of intoxication can the bike be started. System construction is done by sensor actions.

关键词： Cloud computing Head Road accidents Switches Alcoholic beverages Position measurement Safety

来源：评论

学校读者我要写书评

暂无评论

Classification of Awareness in Disorders of Consciousness Using Common Spatial Pattern 13

Classification of Awareness in Disorders of Consciousness Us...

引用

13th International Winter Conference on Brain-computer Interface, BCI 2025

作者： Lee, Chaewon Lee, Sunho Annen, Jitka Jeong, Ji-Hoon Massimini, Marcello Casarotto, Silvia Boly, Melanie Bodart, Olivier Thibaut, Aurore Rosanova, Mario Laureys, Steven Gosseries, Olivia Lee, Minji Dept. Data Science The Catholic University of Korea Bucheon Korea Republic of Dept. Biomedical Software Engineering The Catholic University of Korea Bucheon Korea Republic of Dept. GIGA-Research & Neurology University and University Hospital of Liege Liege Belgium Dept. Data Analysis University of Ghent GhentB9000 Belgium Dept. Computer Science Chungbuk National University Cheongju Korea Republic of Dept. Biomedical and Clinical Sciences "L. Sacco" University of Milan Milan Italy Wisconsin Institute for Sleep and Consciousness Dept. Psychiatry University of Wisconsin Madison United States Coma Science Group GIGA-Consciousness GIGA Research Center University of Liège Liège Belgium Centre du Cerveau Neurology department University Hospital of Liège Liège Belgium

ISBN: (纸本)9798331521929

Advances in intensive care have improved the survival rate of patients with severe acute brain injury, but diagnostic errors for patients with disorders of consciousness are still high. Accurate diagnosis of these patients is very important because effective treatment can vary depending on the diagnosis. In this study, we propose a framework for classifying unresponsive wakefulness syndrome and minimally conscious state, focusing on awareness. In particular, power spectral density and common spatial patterns were used together, considering that spatial information is a key feature in consciousness. The 16 patients with unresponsive wakefulness syndrome and 14 with minimally conscious state underwent resting-state electroencephalography measurements. In addition, we compared the performance by utilizing each frequency (delta, theta, alpha, beta, gamma bands) related to consciousness. As a result, the highest accuracy of 95.06% was achieved by the EEGNet classifier, especially in the beta frequency band. We demonstrated that spatial information is very important in consciousness, as we observed that classification performance improved when common spatial patterns were used. These results provide insight into various frameworks for diagnosing patients with disorders of consciousness and may help patients survive by increasing the diagnosis rate in the future. © 2025 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

PAC PREDICTION SETS UNDER COVARIATE SHIFT 10

PAC PREDICTION SETS UNDER COVARIATE SHIFT

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Park, Sangdon Dobriban, Edgar Lee, Insup Bastani, Osbert Dept. of Computer & Info. Science PRECISE Center University of Pennsylvania United States Dept. of Statistics & Data Science The Wharton School University of Pennsylvania United States

An important challenge facing modern machine learning is how to rigorously quantify the uncertainty of model predictions. Conveying uncertainty is especially important when there are changes to the underlying data distribution that might invalidate the predictive model. Yet, most existing uncertainty quantification algorithms break down in the presence of such shifts. We propose a novel approach that addresses this challenge by constructing probably approximately correct (PAC) prediction sets in the presence of covariate shift. Our approach focuses on the setting where there is a covariate shift from the source distribution (where we have labeled training examples) to the target distribution (for which we want to quantify uncertainty). Our algorithm assumes given importance weights that encode how the probabilities of the training examples change under the covariate shift. In practice, importance weights typically need to be estimated;thus, we extend our algorithm to the setting where we are given confidence intervals for the importance weights. We demonstrate the effectiveness of our approach on covariate shifts based on DomainNet and ImageNet. Our algorithm satisfies the PAC constraint, and gives prediction sets with the smallest average normalized size among approaches that always satisfy the PAC constraint. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Self Attention in U-Net for Semantic Segmentation of Low Resolution SAR Images 23

Self Attention in U-Net for Semantic Segmentation of Low Res...

引用

2023 Asia Conference on computer Vision, Image Processing and Pattern Recognition, CVIPPR 2023

作者： Yadav, Hrishikesh Singh Panchal, Priyanshu Manawat, Divyanshu Girisha, S. Shreesha, S. Dept. of Data Science and Computer Applications Manipal Institute of Technology Manipal Academy of Higher Education Manipal India Dept. of Information and Communication Technology Manipal Institute of Technology Manipal Academy of Higher Education Manipal India

ISBN: (纸本)9798400700033

The SAR image semantic segmentation using computer vision techniques has gained much popularity in the research community due to their wide applications. Despite the advancements in Deep Learning for image analysis, these models still struggle to segment SAR images due to the existence of speckle noise and a poor feature extractor. Moreover, deep learning models are challenging to train on small datasets and the performance of the model is significantly impacted by the quality of the data. This calls for the development of an effective network that can draw out critical information from the low resolution SAR images. In this regard, the present work proposes a unique Self attention module in U-Net for the semantic segmentation of low resolution SAR images.. The Self Attention Model makes use of Laplacian kernel to highlight the sharp discontinuities in the features that define the boundaries of the objects. The proposed model, employs dilated convolution layers at the initial layers, enabling the model to more effectively capture larger contextual information. With an accuracy of 0.84 and an F1-score of 0.83, the proposed model outperforms the state-of-the-art techniques in semantic segmentation of low resolution SAR images. The results clearly demonstrate the importance of the self attention module and the consideration of dilated convolution layers in the initial layers in semantic segmentation of low resolution SAR images. © 2023 ACM.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Exploiting Interdisciplinary Research Design for Temporally Complex Big data: Discussion of a Case-Study Using on Heterogenous Bibliographic Big data

引用

Proceedings of the Association for Information science and Technology 2022年第1期59卷 579-582页

作者： Mabry Patricia, L. Brian, Martinson Thomas, Valente Liu, Xiaozhong Research Dept. HealthPartners Institute United States Dept of Medicine University of Minnesota United States University of Southern California Irvine United States Data Science & Computer Science Worcester Polytechnic Institute United States

Artificial Intelligence (AI) methods are valued for their ability to predict outcomes from dynamically complex data. Despite this virtue, AI is widely criticized as a "black box" i.e., lacking mechanistic explanations to accompany predictions. We introduce a novel interdisciplinary approach that balances the predictive power of data-driven methods with theory-driven explanatory power by presenting a shared use case from four disciplinary perspectives. The use case examines scientific career trajectories through temporally complex, heterogeneous bibliographic big data. Topics addressed include: data representation in complex problems, trade-offs between theoretical, hypothesis-driven, and data-driven approaches, AI trustworthiness, model fairness, algorithm explainability and AI adoption/usability. Panelists and audience members will be prompted to discuss the value of approach presented versus other ways to address the challenges raised by the panel, and to consider their limitations and remaining challenges. 85 Annual Meeting of the Association for Information science & Technology | Oct. 29 – Nov. 1, 2022 | Pittsburgh, PA. Author(s) retain copyright, but ASIS&T receives an exclusive publication license.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

An Optimized Steganographic Technique for 24-Bit Digital Images using Slab Partitioning

An Optimized Steganographic Technique for 24-Bit Digital Ima...

引用

International Conference on ent Computing and Control Systems (ICICCS)

作者： Pinaki Pratim Acharjya Jayeeta Majumdar Subhabrata Barman Jayashri Deb Sinha Ramsundar Ghorai Arpan Ghosh Dept. of Computer Science and Engineering Haldia Institute of Technology Haldia West Bengal India Dept. of Computer Science and Engineering (Data Science) Haldia Institute of Technology Haldia West Bengal India

ISBN: (数字)9798331512088

ISBN: (纸本)9798331512095

Based on image slabs and sheets, a novel kind of image steganography method for digital images has been proposed in this research work. Using the binary representation of the pixel, this approach splits the cover image into 24 fixed-size sheets. The secret message's binary counterpart is then incorporated into the cover image. It looks through each sheet's rows and columns to locate the one that most closely matches the secret message's binary counterpart. The row or column's position and how it differs from the message it stores in the LSB slab. Compared to previous ways, the proposed technique somewhat modifies the cover image.

关键词： Image quality Steganography Visualization Digital images Control systems Robustness Slabs

来源：评论

学校读者我要写书评

暂无评论

Enhancing Blind Communication With Voice-Assisted Email

Enhancing Blind Communication With Voice-Assisted Email

引用

Expert Clouds and Applications (ICOECA), International Conference on

作者： C. Sasikala Rupalakshmi M Sameer Ahammad S Meghana U Harshad Ali M Dept. Computer Science and Engineering Srinivasa Ramanujan Institute of Technology Anantapur India Dept. Computer Science and Engineering(Data Science) Srinivasa Ramanujan Institute of Technology Anantapur India

ISBN: (数字)9798350385793

ISBN: (纸本)9798350385809

Considering the key role of the internet in daily life, accessibility becomes crucial, especially for visually impaired individuals who heavily rely on it for accessing information. However, a significant portion of text materials on the internet remains inaccessible to blind users, limiting their opportunities for development and inclusion in various communities worldwide. Leveraging audio virtual environments, predominantly through screen reader technology, offers a notable advantage for blind individuals in accessing online applications like emails. This study presents a new design aimed at facilitating the email retrieval for blind users with the utilization of speech-to-text and text-to-speech technologies. This approach is particularly suitable for individuals with average human capabilities and a limited level of education, as it relies solely on interactive voice response for input, ensuring effective functionality for the proposed system.

关键词： Productivity Navigation Virtual environments User interfaces Electronic mail Text to speech Standards

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：