检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Jnini, Anas Vella, Flavio Zeinhofer, Marius Dept. of Information Engineering and Computer Science University of Trento Italy Simula Research Laboratory Oslo Norway

We propose Gauss-Newton’s method in function space for the solution of the Navier-Stokes equations in the physics-informed neural network (PINN) framework. Upon discretization, this yields a natural gradient method that provably mimics the function space dynamics. Our computational results demonstrate close to single-precision accuracy measured in relative L2 norm on a number of benchmark problems. To the best of our knowledge, this constitutes the first contribution in the PINN literature that solves the Navier-Stokes equations to this degree of accuracy. Finally, we show that given a suitable integral discretization, the proposed optimization algorithm agrees with Gauss-Newton’s method in parameter space. This allows a matrix-free formulation enabling efficient scalability to large network sizes. Copyright © 2024, The Authors. All rights reserved.

关键词： Viscous flow

来源：评论

学校读者我要写书评

暂无评论

Addressing Misinformation in Bengali Media: A Hybrid Deep Learning Solution

Addressing Misinformation in Bengali Media: A Hybrid Deep Le...

引用

International Conference on computer and information Technology (ICCIT)

作者： Fuad Ibne Jashim Farhad Shah Imran Md Mehedi Hasan Santo Mahbub Khan Anamul Sakib Md Shahidur Rahman Md Ariful Islam Rezaul Haque Shafiur Rahman Dept. of Information Technology CQ University Australia Dept. of Computer Science and Engineering BRAC University Bangladesh Dept. of Management Information System Pacific State University USA Dept. of Business Administration International American University USA Dept. of Engineering Management Westcliff University USA Dept. of Computer Science and Engineering East West University Bangladesh Dept. of Software Engineering Daffodil International University Bangladesh

ISBN: (数字)9798331519094

ISBN: (纸本)9798331519100

The spread of fake news poses significant threats to society, democracy, and public discourse. This is especially true in Bengali-speaking communities where digital literacy and language-specific resources are limited. To address this issue, we urgently need effective ways to detect and mitigate fake news in the Bengali language. This paper highlights the unique challenges associated with linguistic diversity and misinformation prevalence. Our research introduces a hybrid deep learning algorithm specifically designed to classify fake and authentic Bengali news articles. The methodology involves extensive data collection, rigorous preprocessing to improve textual quality, and the use of advanced feature extraction methods. We combined and trained CNN and LSTM/BiLSTM models to handle the nuances of Bengali text. Our proposed algorithm significantly outperforms existing models, with a high accuracy of 98.45% in distinguishing between fake and authentic news and reducing false positives. Additionally, we developed a user-friendly web application that allows general public to input news articles and obtain predictions on their authenticity in real-time. This study not only advances the field of fake news detection but also provides essential tools for journalists, policymakers, and the general public to combat misinformation in Bengali media. Our findings have broader implications, promoting informed public discourse and supporting the development of resilient digital ecosystems. This underscores the need for ongoing research and adaptation of such models to combat the global challenge of fake news in various languages and contexts.

关键词： Deep learning Machine learning algorithms Social networking (online) Biological system modeling Scalability Ecosystems Text categorization Classification algorithms Cultural differences Fake news

来源：评论

学校读者我要写书评

暂无评论

neuROSym: Deployment and Evaluation of a ROS-based Neuro-Symbolic Model for Human Motion Prediction

arXiv

引用

arXiv 2024年

作者： Mghames, Sariah Castri, Luca Hanheide, Marc Bellotto, Nicola School of Computer Science University of Lincoln United Kingdom Dept. of Information Engineering University of Padua Italy

Autonomous mobile robots can rely on several human motion detection and prediction systems for safe and efficient navigation in human environments, but the underline model architectures can have different impacts on the trustworthiness of the robot in the real world. Among existing solutions for context-aware human motion prediction, some approaches have shown the benefit of integrating symbolic knowledge with state-of-the-art neural networks. In particular, a recent neuro-symbolic architecture (NeuroSyM) has successfully embedded context with a Qualitative Trajectory Calculus (QTC) for spatial interactions representation. This work achieved better performance than neural-only baseline architectures on offline datasets. In this paper, we extend the original architecture to provide neuROSym, a ROS package for robot deployment in real-world scenarios, which can run, visualise, and evaluate previous neural-only and neuro-symbolic models for motion prediction online. We evaluated these models, NeuroSyM and a baseline SGAN, on a TIAGo robot in two scenarios with different human motion patterns. We assessed accuracy and runtime performance of the prediction models, showing a general improvement in case our neuro-symbolic architecture is used. We make the neuROSym package publicly available to the robotics community. © 2024, CC BY-NC-SA.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Game Theoretic Analysis of AoI Efficiency for Participatory and Federated Data Ecosystems

Game Theoretic Analysis of AoI Efficiency for Participatory ...

引用

IEEE International Conference on Communications Workshops, ICC

作者： Alessandro Buratto Alessio Mora Armir Bujari Leonardo Badia Dept. of Information Engineering (DEI) University of Padova Italy Dept. of Computer Science and Engineering University of Bologna Italy

We investigate the Age of information (AoI) of status updates, resulting from the convergence of multiple and federated data sources subject to both independent and voluntary participation. In this setting, the effectiveness of the status update requires the simultaneous intervention and aggregation of multiple data, according to a parametric function. Given the distributed nature of the problem, such a setup lends itself to a game theoretic approach, whereby strategic intelligent users act in a distributed fashion towards the maximization of their individual utility. The latter is chosen as a combination of the global AoI resulting from the data aggregation and parametrized by a tunable function, and an individual cost term. We compute the Nash equilibrium of the resulting allocation, and show interesting consequences of the strategic decisions made by the players.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Solutions to Predict the Impact of Lung Cancer with an Advanced Intelligent Computing Method 5

Evaluating the Solutions to Predict the Impact of Lung Cance...

引用

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

作者： Sundar, R. Ramadass, Sudhir Meeha, D. Subramanian, Balambigai Shankar, S. Siva Parasa, Gayatri Madanapalle Institute of Technology and Science Dept. of Computer Science and Engineering India Sterck Systems Chennai India Dr. Rangarajan Dr. Sakunthala Engg College Vel Tech Multi Tech Dept. of Information Technology Avadi Chennai India Dept. of Ece Kongu Engineering College Perundurai India Kg Reddy College of Engineering and Technology Dept. of Cse -AIandML Telangana Chilukuru India Koneru Lakshmaiah Education Foundation Dept. of Cse Vaddeswaram Andhra Pradesh Guntur India

ISBN: (纸本)9781665474672

Using symptoms as a basis for diagnosing lung cancer, Lung cancer detection was accomplished using several different machine-learning regression strategies. By comparing the efficacy of several regression algorithms for predicting lung cancer, considering factors including age, gender, chest discomfort, shortness of breath, alcohol intake, chronic illness, trouble swallowing, anxiety, and peer pressure. Lung cancer predictions and evaluations are made using regression methods such as the linear algorithm, polynomial regression, logistic regression, logarithmic regression, and multiple regression. With a predictive accuracy of 96%, multiple regression is superior to other regression techniques when identifying future lung cancer cases. The r-squared value, which can be calculated using several regression machine learning approaches, may also be used to evaluate the association between the various symptoms and lung cancer. Lung cancer is diagnosed using the r-squared value, which is calculated using several algorithms and takes into symptoms, including chronic illness. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Self-Optimizing Distributed Cloud Computing with Dynamic Neural Resource Allocation and Fault-Tolerant Multi-Agent Systems 4

Self-Optimizing Distributed Cloud Computing with Dynamic Neu...

引用

4th International Conference on Ubiquitous Computing and Intelligent information Systems, ICUIS 2024

作者： Tripura, N. Divya, P. Chaganti, Koushik Reddy Rao, Kota Venkateswara Rajyalakshmi, P. Naresh, P. Vignan Institute of Technology And Science Dept of Mba Hyderabad India University of the Cumberlands Dept. of Computer and Information Systems KY United States Andhra Loyola Institute of Engineering and Technology Dept of Cse Vijayawada India Tkr College of Engineering and Technology Dept of Cse Hyderabad India Dayananda Sagar University Dept of Cse Bangalore India

ISBN: (纸本)9798331529635

The exponential growth of distributed cloud systems necessitates an intelligent form of workload management that ensures optimum performance, scalability, and reliability. Traditional approaches based on static or heuristic resource allocation and fault-tolerance mechanisms cannot capture the dynamic nature of modern workloads and heterogeneous infrastructures. Drawing from this source of inspiration, this work develops a holistic framework integrating machine learning models that facilitate self-optimizing distributed cloud computing for dynamic workload management. Three components are significant in the proposed framework: (1) DNRA;this uses a hybrid GNN and RL architecture for real-time resource allocation, offering up to 25% improvement in resource utilization and a 30% reduction in task latency. (2) Workload-Aware Transfer Learning Scheduler (WATLS), leveraging transfer learning to predict workload dynamics across heterogeneous nodes, achieving 20% higher task throughput and 15% energy savings through proactive scheduling. (3) Multi-Agent Predictive Fault-Tolerant System (MAP-FTS), combining multi-agent systems with predictive fault detection to preemptively redistribute tasks and schedule maintenance, reducing system downtime by 50% and enhancing fault detection accuracy to 90%. The framework integrates novel methodologies towards answering the main challenges of resource allocation, workload prediction, and fault tolerance. The amount of progress achieved through cumulative contributions includes improvement in system reliability and scalability up to 5x their nodes and respective scalable energy efficiency without any degradation of performance. This work paves the pathway for an adaptive and intelligent next generation of distributed cloud systems. © 2024 IEEE.

关键词： Distributed cloud

来源：评论

学校读者我要写书评

暂无评论

Exploring Explainable AI in Large Language Models: Enhancing Transparency and Trust

Exploring Explainable AI in Large Language Models: Enhancing...

引用

International Conference on Advanced computer Control, ICACC

作者： Ijas A. H Ashly Ann Jo Ebin Deni Raj Dept. of Computer Science & Engineering FACTS-H Lab Indian Institute of Information Technology Kottayam India

ISBN: (数字)9798350379136

ISBN: (纸本)9798350379143

Large Language Models (LLMs) are at the forefront of technological evolution, significantly enhancing digital interactions and automating complex processes across various sectors. While these models facilitate advancements in data analytics, content generation, and strategic decision-making, their opaque nature poses challenges regarding user trust and model comprehension. Addressing the critical need for transparency, this paper focuses on enhancing LLM explainability. We propose a framework to demystify the internal mechanisms of these models, facilitating a deeper understanding that aligns with stringent ethical standards. Our approach integrates advanced explanatory tools that elucidate model decisions and foster accountability and fairness in Artificial Intelligence applications. Through rigorous analysis and the development of novel interpretative methodologies, we aim to bridge the gap between LLM capabilities and ethical AI practices, ensuring that these powerful tools are leveraged responsibly and transparently in critical infrastructures.

关键词： Ethics Analytical models Data analysis Explainable AI Large language models Computational modeling Decision making Data models Critical infrastructure Standards

来源：评论

学校读者我要写书评

暂无评论

Scalability in Autoencoder-based OFDM Communication System 2

Scalability in Autoencoder-based OFDM Communication System

引用

2nd IEEE International Conference on computer Vision and Machine Intelligence, CVMI 2023

作者： Tsugawa, Seizan Toma, Takao Oshiro, Shiho Wada, Tomohisa University of the Ryukyus Computer Science and Intelligent Systems Program Okinawa Japan Magna Design Net Inc Okinawa Japan University of the Ryukyus Information Technology Center Okinawa Japan University of the Ryukyus Area of Computer Science and Intelligent Systems Dept. of Engineering Okinawa Japan

ISBN: (纸本)9798350305142

This paper proposed Scalability in Autoencoder-based Orthogonal Frequency Division Multiplexing(OFDM) communication system. In the previous research, only the comparison between IEEE802.11a and Autoencoder by the conventional OFDM communication system was performed, and it was proved that the communication system created by Autoencoder exceeded the performance of the conventional system. Therefore, in this paper, it uses IEEE802.11n and compare whether it can be improved by expanding the bandwidth and using ***802.11n standard has an FFT length of 128, a subcarrier number of 114 (108 for data), and modulation schemes of Quadrature Phase Shift Keying(QPSK), 16 Quadrature Amplitude Modulation (16QAM). The GI length is 800ns and the symbol length is 4000ns. In the simulation, a computer simulation was performed using a conventional OFDM communication system and a communication system generated by Autoencoder. Assuming that the simulation environment had an Signal-to-Noise Ratio (SNR) of 0 to 30 and an amplitude r of 0.0 to 1.0, the Symbol Error Rate (SER) status for each SNR was output. As a result of computer simulation, QPSK converged at SNR 27 at IEEE 802.11a, but was able to reduce SER overwhelmingly to SNR 12 at IEEE 802.11n. Also, in 16QAM the convergence at r=0.0 is the same as for SNR22 , but in IEEE 802.11a it does not converge after r=0.6, but in IEEE 802.11n it does not converge only at r=0.9 and r=1.0. As a future task, it will use IEEE802.11ac, which enables communication speeds several times faster than IEEE802.11n, examine whether it is possible to further improve accuracy. And it will continue our research to correspond MIMO communication. © 2023 IEEE.

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Microstrip Patch Antenna for Single Resonant Frequency Using Various Types of Slots

Microstrip Patch Antenna for Single Resonant Frequency Using...

引用

Electrical, computer, Communications and Mechatronics engineering (ICECCME), International Conference on

作者： Md Amirul Islam Giovanni Stea Md Ashraf Uddin Sultan Mahmud Kh. Mustafizur Rahma Dept. of Information Engineering University of Pisa Pisa Italy Dept. of Computer Science & Engineering Jagannath University Dhaka Bangladesh Dept. of Computer Science & Engineering World University Of Bangladesh Dhaka Bangladesh

Microstrip patch antennas are widely utilized in WLAN applications, and body-centric wireless communication relies on multiple network links to get messages through. But the existing antenna size is big with less bandwidth, which increases the cost. This paper has taken a rigorous approach to design an antenna that will provide a single resonant frequency at the targeted bandwidth (2.45GHz). The patch size in the proposed antenna is 28mm by 27mm and energized by a 50 ohm microstrip feed line with dimensions 3.137mm by 18.35mm. The dielectric substrate of permittivity E r = 4.3 is used in the fabrication process. The optimal size and other antenna characteristics are found by finite difference time domain method based CST Studio Suite. Other parameters like return loss, input impedance, and bandwidth of the microstrip patch antennas are calculated using VNA and WATS software to verify the proposed work. Finally, the proposed slot-loaded antenna attains an improved bandwidth and gain while providing a single resonant frequency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recognition of Wh-Question Sign Gestures in Video Streams using an Attention Driven C3D-BiLSTM Network

引用

Procedia computer science 2024年 235卷 2920-2931页

作者： Arnab Dey Samit Biswas Dac-Nhuong Le Dept. of Computer Science and Technology Indian Institute of Engineering Science and Technology Shibpur Howrah 711103 India Faculty of Information Technology Haiphong University Haiphong 180000 Vietnam

Human sign language is a visual and gestural means of communication used by people with hearing impairments to interact with others. It has the potential to enable interaction between individuals who struggle with verbal communication and those who lack the essential proficiency to comprehend sign language. Wh-questions constitute a substantial portion of daily sign language interactions. Automatic recognition of Wh-question words in sign language, encompassing interrogative words, has received limited attention in gesture recognition. In this context, a novel dataset named the American Question Sign Video dataset (AQSVd) has been introduced as a significant contribution. Recognizing Wh-question signs in video streams empowers individuals to effectively convey messages through hand movements and gestures, fostering inclusivity and accessibility in communication for deaf and hearing-impaired individuals. The paper proposes a Deep Convolutional-3D BiLSTM Multi-head Attention network for recognizing American Wh-Question word sign gestures in video streams. Incorporating Multi-head attention in the proposed model enhances its ability to capture intricate spatial and temporal features, essential for accurate gesture recognition. The proposed model is thoroughly evaluated across a range of datasets, such as INCLUDE50, WLASL-100, and our AQSVd dataset, achieving remarkable results. Specifically, our model demonstrated an outstanding 98.91% validation accuracy on the AQSVd dataset. The C3D-BiLSTM MHAttention model outperforms other state-of-the-art models, demonstrating its superiority in sign language recognition tasks. The proposed dataset and C3D-BiLSTM Multi-head Attention model contribute significantly to this field, offering potential benefits in education, human-robot interaction, and overall communication for the hearing-impaired community.

关键词： Gesture Recognition Wh-Question American Sign Language Video Streams Multi-head Attention C3D-BiLSTM

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：