检索结果-内蒙古大学图书馆

Chemical environment adaptive learning for optical band gap prediction of doped graphitic carbon nitride nanosheets

Neural Computing and Applications 2025年第5期37卷 3287-3301页

作者： Chen, Chen Xu, Enze Yang, Defu Yan, Chenggang Wei, Tao Chen, Hanning Wei, Yong Chen, Minghan Intelligent Information Processing Laboratory Hangzhou Dianzi University Hangzhou China Department of Computer Science Wake Forest University Winston-SalemNC United States Department of Chemical Engineering Howard University WashingtonDC United States Texas Advanced Computing Center University of Texas at Austin AustinTX United States Department of Computer Science & Information Systems University of North Georgia DahlonegaGA United States

This study presents a new machine learning algorithm, named Chemical Environment Graph Neural Network (ChemGNN), designed to accelerate materials property prediction and advance new materials discovery. Graphitic carbon nitride (g-C3N4) and its doped variants have gained significant interest for their potential as optical materials. Accurate prediction of their band gaps is crucial for practical applications;however, traditional quantum simulation methods are computationally expensive and challenging to explore the vast space of possible doped molecular structures. The proposed ChemGNN leverages the learning ability of current graph neural networks (GNNs) to satisfactorily capture the characteristics of atoms' chemical environment underlying complex molecular structures. Our experimental results demonstrate more than 100% improvement in band gap prediction accuracy over existing GNNs on g-C3N4. Furthermore, the general ChemGNN model can precisely foresee band gaps of various doped g-C3N4 structures, making it a valuable tool for performing high-throughput prediction in materials design and development. © The Author(s) 2024.

关键词： Graphitic Carbon Nitride

来源：评论

学校读者我要写书评

暂无评论

Cardiac MRI Segmentation of Ventricular Structures and Myocardium Using U-Net Variants 5

Cardiac MRI Segmentation of Ventricular Structures and Myoca...

引用

5th International Conference on Advanced Research in Computing, ICARC 2025

作者： Wijesinghe, Chinthalanka B. Meedeniya, Dulani Yogarajah, Pratheepan University of Moratuwa Department of Computer Science and Engineering Moratuwa Sri Lanka Ulster University School of Computing Engineering and Intelligent Systems Londonderry United Kingdom

ISBN: (纸本)9798331530983

Accurate segmentation of the ventricular structures and myocardium from Cardiac Magnetic Resonance (CMR) images is essential to diagnose and manage cardiovascular diseases. This study systematically evaluates the performance of five U-Net variants in cardiac MRI segmentation using the Automated Cardiac Diagnosis Challenge (ACDC) dataset and a hybrid loss function combining Cross-Entropy and dice losses. Among the variants, the Feature Pyramid U-Net achieved the best performance, with Dice coefficients of 0.9388 (Left Ventricle), 0.8759 (Right Ventricle), and 0.8426 (Myocardium), showcasing its superior ability to capture multi-scale features and segment complex anatomical structures. The comprehensive and standardized evaluation conducted in this study provides valuable insights into the strengths and limitations of these architectures for cardiac segmentation. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Autonomous 3D Reconstruction with Small Unmanned Aerial Vehicle (UAV) using Structure from Motion: Practical Aspects

Autonomous 3D Reconstruction with Small Unmanned Aerial Vehi...

引用

AIAA science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Rayon, Nathan Stevens, Raymond Sevil, Hakki Erhan Department of Computer Science University of West Florida FL32514 United States Department of Electrical and Computer Engineering University of West Florida FL32514 United States Department of Intelligent Systems & Robotics University of West Florida FL32514 United States

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

This paper explores the practical considerations and challenges involved in achieving autonomous 3D reconstruction utilizing small Unmanned Aerial Vehicles (UAVs) through the framework of Structure from Motion (SFM). The utilization of small UAVs equipped with lightweight cameras presents a promising resource for cost-effective and rapid 3D mapping in various domains such as disaster response, infrastructure inspection, and search and rescue. In this study, the critical practical aspects of this process, including height level for taking images, UAV selection, number of images, image acquisition strategies, and computational time. The effectiveness and limitations of autonomous 3D reconstruction with small UAVs through practical insights are summarized, with discussions on potential advancements and areas for future research. This paper serves as a guide for researchers interested in utilizing small UAVs for autonomous 3D reconstruction tasks applications. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

The Role of Generative AI in Deepfake Detection: A Systematic Literature Review

The Role of Generative AI in Deepfake Detection: A Systemati...

引用

International Conference on Smart Business and technology, ICSBT 2024

作者： Acim, Btissam Kharmoum, Nassim Lagmiri, Souad Najoua Ziti, Soumia Department of Computer Science Intelligent Processing & Security of Systems Faculty of Sciences Mohammed V University in Rabat Rabat Morocco Rabat Morocco IT Networking Security and Management Laboratory Higher Institute of Management Administration and Computer Engineering Rabat Morocco

ISBN: (纸本)9783031866975

There is a possibility that deepfakes will increase a great deal of false information in a very realistic way, but it seems that today such technology appears to be extremely dangerous. While generative Artificial Intelligence (AI) does expand possibilities and give an opportunity to achieve terrific outcomes and has innumerable potential uses. This systematic literature review focuses on the role of generative AI in the improvement of deepfake detection technologies, providing a comparison between different methods and assessing their effectiveness. By analyzing recent studies, it depicts the techniques employed most frequently in deepfake detection, such as the ones concentrating on the intricacies between the visual and auditory elements, the temporal domains, as well as any minor signs of alteration. Due to the fact that generative AI is rapidly improving, the methods that are used to detect its use are often inadequate, which calls for more studies on the subject matter. Besides, by combining audio and visual elements when performing the analysis, calling it as a method that can be useful in focusing the detection growth potential with diverse and unstructured data. Also, this study evaluates the advantages and limitations of the techniques existing today and demonstrates their relative effectiveness in controlled and real conditions. Clarifying that measures aimed at detecting AI generated content should be preoccupied with a technique that is able to keep pace with changes in generative AI. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Immoral post detection using a one-dimensional convolutional neural network-based LSTM network

引用

Multimedia Tools and Applications 2025年 1-20页

作者： Saqia, Bibi Khan, Khairullah Rahman, Atta Ur Khan, Aurangzeb Jain, Deepak Kumar Department of Computer Science University of Science and Technology Bannu28100 Pakistan Riphah Institute of Systems Engineering Riphah International University Islamabad46000 Pakistan Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology Dalian116024 China Symbiosis Institute of Technology Symbiosis International University Pune India

In text mining and Natural Language Processing (NLP), extracting emotions from textual data is gaining rapid attraction. The proliferation of online content and the freedom of expression on social media platforms has compelled the advancement of more sophisticated methods for the automatic identification of unwanted content. The One-Dimensional Convolutional Neural Network (1D-CNN) performs best for feature extraction, while the Long Short-Term Memory Network (LSTM) is well-known for extracting sequential features and classification of textual data. This study proposes a novel solution by combining 1D-CNN with LSTM. Utilizing a context-aware model, this study aims to enhance the detection of immoral posts, including hate speech and other forms of immoral content on social media platforms. Various posts are extracted from social media, which are then processed using Glove word embedding models. It depicts the word representations in the text, which yields the form of a real-valued vector determining the words' meaning. The 1D convolution utilizes a filter window over the input time-series data to extract features. Relying on the acquired parameters of the filters, they act as feature extractors. This feature extraction technique allows the model to distinguish detailed patterns and nuances from the textual contents of posts. The sequential processing capabilities of the LSTM network enable an in-depth examination of the text, capturing temporal relationships and context, which is critical for successful content categorization. To validate the proposed model, we utilized a benchmark dataset, called the Twitter dataset. The proposed model achieved the highest accuracy of 95.37% and outperforms state-of-the-art works. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A variable structure model of neurons’ application in computer vision

引用

Multimedia Tools and Applications 2025年 1-11页

作者： Sridi, Alaeddine Attia, Mouna Bouallegue, Kais Electronics and Micro-Electronics Laboratory Faculty of Sciences of Monastir University of Monastir Monastir Tunisia The Higher Institute of Computer Science and Communication Technologies of Hammam Sousse University of Sousse Sousse Tunisia Laboratory of Computer Science Parallelism and Intelligent Communicating Systems Faculty of Sciences of Tunisia University of Tunis ELManar Tunis Tunisia Department of Electrical Engineering Higher Institute of Applied Sciences and Technology of Sousse University of Sousse Sousse Tunisia

The neuron doctrine defines the neuron as the basic unit of the nervous system, which drives the dynamic behavior of our organs. This has led to neurons becoming the focus of modern neuroscience research and to the rise of neurocomputing, in which we try to digitally simulate human behavior. The goal being to better understand the human nervous system and gain more control over neuron-related diseases, helping doctors establish faster and more reliable medical diagnoses. In this context, we aim to simulate eye diseases and vision problems by convolving input images using a new class of neural networks based on a variable structure model of neurons presented in [1]. In this work, we focus on recreating the common convolution filters as a first step. This is the first time in neurocomputing literature that dendritic neurons have been used for dynamic convolution kernels generation and eye diseases simulation. We start with a presentation of our upgrades to the model’s flexibility and accuracy. Then, we propose a novel kernel generator algorithm to convolve the input images. Finally, we show its promising results in creating the outline, pixelization, and night convolution kernels, as well as control some metrics, including brightness and data retention. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Parameters Extraction of Photovoltaic Cell Using Particle Swarm Optimization 4th

Parameters Extraction of Photovoltaic Cell Using Particle Sw...

引用

4th International Conference on Electronic Engineering and Renewable Energy systems, ICEERE 2024

作者： Chermite, Charaf Douiri, Moulay Rachid Elamri, Oumaymah Control and Computer Science for Intelligent Systems and Green Energy Department of Applied Physics Faculty of Science and Technology Cadi Ayyad University Marrakech Morocco LAMIGEP EMSI of Marrakech Systems and Applications Engineering Laboratory National School of Applied Sciences Cadi Ayyad University Marrakech Marrakesh Morocco

ISBN: (纸本)9789819799749

Extracting parameters accurately and effectively from solar photovoltaic (PV) models is crucial for detailed simulation, evaluation, and management of PV systems. Although there has been an increase in the development of analytical, numerical, and metaheuristic methods targeting this task, accurately determining these parameters continues to be a significant challenge. This study focuses on applying Particle Swarm Optimization (PSO) for the extraction of key parameters of RTC France solar cells, a critical step towards enhancing PV system efficiency and reliability. Additionally, the PSO's performance is evaluated against other metaheuristic algorithms including Enhanced Chaotic JAYA (CJAYA), Performance-Guided JAYA (PGJAYA), and Enhanced Gradient-Based Optimizer (EGBO), underscoring the effectiveness of the proposed PSO-based approach. Utilizing MATLAB-SIMULINK, comprehensive analysis and results are presented, shedding light on the efficacy of PSO in addressing the intricacies of parameter extraction in PV systems. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Tolerant Tracking Control Protocol for PMSM Based on Policy Iteration Algorithm and Fault Compensation 16th

Tolerant Tracking Control Protocol for PMSM Based on Polic...

引用

16th International Conference on Social Robotics, ICSR + InnoBiz 2024

作者： Yan, Shuya Li, Xiaocong Qian, Huaming Ma, Jun Al Mamun, Abdullah College of Intelligent Systems Science and Engineering Harbin Engineering University Harbin150001 China Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore Guangzhou China Information Science and Technology Eastern Institute of Technology Ningbo China

ISBN: (纸本)9789819611508

In robotics applications, ensuring reliable performance in the presence of actuator faults is essential for maintaining system safety and reliability. This paper presents a tolerant tracking control method for permanent magnet synchronous motors (PMSMs) based on adaptive dynamic programming and fault compensation. The method simultaneously considers tracking accuracy and energy consumption through a policy iteration algorithm. In the optimality analysis of the algorithm, more relaxed conditions are provided to demonstrate that the performance function can converge to a near-optimal value within a finite number of iterations. In practical implementation, an actor-critic network is used to approximate the performance function and control protocol, alongside a fault detection mechanism based on an expanded time horizon, which achieves fault detection from arbitrary initial values. The effectiveness of the proposed algorithm is verified using a high-fidelity PMSM model in Simulink. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

XMeta-OS: A Conceptual Framework for Unified Resource Management in Distributed Edge-Cloud Environments 3rd

XMeta-OS: A Conceptual Framework for Unified Resource Manag...

引用

3rd International Conference on Advances in Computing Research, ACR 2025

作者： Zacharioudakis, Eleftherios Kakoulli, Elena Evripidou, Salomi Intelligent Systems Laboratory Department of Computer Science Neapolis University Pafos Pafos Cyprus National Technical University of Ukraine Igor Sikorsky Kyiv Polytechnic Institute Kyiv Ukraine Electrical Engineering and Computer Engineering and Informatics Cyprus University of Technology Limassol Cyprus

ISBN: (纸本)9783031876462

This paper introduces XMeta-OS, a meta-operating system specially designed with Linux as its foundation to unify and optimize resource management for the distributed edge-cloud when dynamic use of GPU resources is possible. This approach offer a new GPU abstraction layer and dynamic edge-cloud allocation model that offer enhanced flexibility and resource utilization over existing systems like Kubernetes and OpenStack. By using likely sensitive data, the model applied cloud-pushed deployment model. XMeta-OS manages computer resources in real-time. Therefore, fulfilling high performance various needs. It allocates CPU and GPU in real-time to workloads requiring massive parallel processing, such as machine learning, scientific simulations, real-time data analytics, and transportation tasks. Fabrication in the laboratory of an edge-cloud environment can help to assess the scalability, fault tolerance and efficiency of the system. It showcases the overall architectural design of XMeta-OS. Changes to the kernel and security solutions for safe and effective distribution are suggested. This article presents the design of the XMeta-OS. The future of XMeta-OS entails usage and testing with which we see latency, energy, computation and other such measurements in labs. XMeta-OS is a solution to cost performance, emerging application, large-scale edge-cloud deployments, and distributed GPU-enabled infrastructures. Meta-Operating System in Edge-Cloud Continuum for dynamic resource management of GPU. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Cluster computing

来源：评论

学校读者我要写书评

暂无评论

AFuNet: an attention-based fusion network to classify texts in a resource-constrained language

引用

Neural Computing and Applications 2025年第9期37卷 6725-6748页

作者： Hossain, Md. Rajib Hoque, Mohammed Moshiul Dewan, M. Ali Akber Hoque, Enamul Siddique, Nazmul Department of Computer Science & Engineering Chittagong University of Engineering & Technology Chittagong4349 Bangladesh School of Computing and Information Systems Faculty of Science and Technology Athabasca University AthabascaABT9S 3A3 Canada School of Information Technology York University TorontoONM3J 1P3 Canada School of Computing Engineering and Intelligent Systems Ulster University Coleraine United Kingdom

In the era of widespread Internet use and extensive social media interaction, the digital realm is accumulating vast amounts of unstructured text data. This unstructured data often contain undesirable information, necessitating time-consuming manual classification efforts. An intelligent text classification system capable of automatically categorizing digitized texts based on semantic meaning is crucial. However, this task is particularly challenging for low-resource languages like Bengali due to a shortage of annotated corpora, issues with out-of-vocabulary words, lack of domain-specific hyperparameter tuning, limited ability to extract generalized text features, and class imbalances within the corpus. AFuNet: an attention-based fusion network to classify texts in a resource-constrained language. AFuNet undergoes a comprehensive four-phase experimental process, including baseline model evaluation and hyperparameter tuning, late fusion and model selection, attention-based early fusion and model identification, and an ablation study with impact analysis. Fine-tuned based on five Bengali text classification corpora, AFuNet achieves impressive accuracies: 96.60 ± 0.2 (BTCC11), 85.37 ± 0.2 (OSBC), 97.35 ± 0.2 (BARD), 93.74 ± 0.2 (IndicNLP), and 96.51 ± 0.2 (ProthomAlo). In comparison with previous state-of-the-art models on these corpora, AFuNet demonstrates significant accuracy improvements ranging from 0.54% to 4.49%, showcasing its effectiveness in advancing text classification capabilities for the Bengali language. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Semantics

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：