检索结果-内蒙古大学图书馆

Air Quality Assessment B ased on CNN Transformer Hybrid Architecture

International Journal of Advanced Computer science and Applications 2025年第4期16卷 273-279页

作者： Zhang, Yuchen Thinakaran, Rajermani Faculty of Data Science and Information Technology INTI International University Malaysia

Air quality assessment plays a crucial role in environmental governance and public health decision making. Traditional assessment methods have limitations in handling multi source heterogeneous data and complex nonlinear relationships. This paper proposes an air quality assessment model based on a CNN Transformer hybrid architecture, which achieves end to end prediction by integrating CNN's local feature extraction capability with Transformer's advantage in modeling global dependencies. The model employs a three layer CNN for local feature learning, combined with Transformer's multi head self attention mechanism to capture long range dependencies, and uses multilayer perceptrons for final prediction. Experiments on public datasets demonstrate that compared t o traditional machine learning methods and single deep learning models, the proposed hybrid architecture achieves a 10.2 percentage improvement in Root Mean Square Error (RMSE) and a 0.57 percentage point improvement in coefficient of determination (R2). T hrough systematic ablation experiments, we verify the necessity of each model component, particularly the importance of the CNN Transformer hybrid architecture, positional encoding mechanism, and multi layer network structure in enhancing prediction perfor mance. The research results provide an effective deep learning solution for air quality assessment. © (2025), (science and information Organization). All Rights Reserved.

关键词： Damage detection

来源：评论

学校读者我要写书评

暂无评论

LesionAid: vision transformers-based skin lesion generation and classification – A practical review

引用

Multimedia Tools and Applications 2025年 1-22页

作者： K, Mallikharjuna Rao Krishna, Ghanta Sai Supriya, Kundrapu Sorgile, Meetiksha Data Science and Artificial Intelligence International Institute of Information Technology Naya Raipur India Computer Science and Engineering International Institute of Information Technology Naya Raipur India

Skin cancer is one of the most prevalent forms of human cancer. It is recognized mainly visually, beginning with clinical screening and continuing with the dermoscopic examination, histological assessment, and specimen collection. Deep convolutional neural networks (CNNs) perform highly segregated and potentially universal tasks against a classified fine-grained object. This study suggests a novel multi-class prediction framework that uses ViT and ViTGAN to categories skin lesions. To address the class disparity, GANs (Generative Adversarial Networks) based on vision transformers are used. The framework comprises four main phases: ViTGANs, Image processing, and explainable AI. Phase 1 consists of generating synthetic images using ViTGAN to balance all the classes in the dataset. To enhance the amount of the data, the second phase involves using various morphological processes and data augmentation techniques. In phases three and four, a ViT model for edge computing systems that can recognize patterns and classify skin lesions from the user's skin that is visible in the picture is developed. In phase 3, after classifying the lesions into the desired class with ViT, we will use explainable AI (XAI) that leads to more explainable results (using activation maps, etc.) while ensuring high predictive accuracy. The results demonstrate that the model used for generating synthetic images has achieved an FID score of 13.32 and the ViT model has achieved 99.2% as its training accuracy and 97.4% as its validation accuracy. The whole framework is compared with the existing frameworks for skin lesion detection. And explainable AI (XAI) is used in the proposed framework in order to increase model transparency and boost trust among users by illustrating the main factors affecting predictions. This interpretability helps physicians in making more informed decisions by providing clear insights into the model's reasoning. © The Author(s), under exclusive licence to Springer science+Bu

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Gloss-driven Conditional Diffusion Models for Sign Language Production

引用

ACM Transactions on Multimedia Computing, Communications and Applications 2025年第4期21卷 1-17页

作者： Tang, Shengeng Xue, Feng Wu, Jingjing Wang, Shuo Hong, Richang School of Computer Science and Information Engineering Hefei University of Technology Hefei China School of Software Hefei University of Technology Hefei China School of Data Science School of Information Science and Technology University of Science and Technology of China Hefei China

Sign Language Production (SLP) aims to convert text or audio sentences into sign language videos corresponding to their semantics, which is challenging due to the diversity and complexity of sign languages, and cross-modal semantic mapping issues. In this work, we propose a Gloss-driven Conditional Diffusion Model (GCDM) for SLP. The core of the GCDM is a diffusion model architecture, in which the sign gloss sequence is encoded by a Transformer-based encoder and input into the diffusion model as a semantic prior condition. In the process of sign pose generation, the textual semantic priors carried in the encoded gloss features are integrated into the embedded Gaussian noise via cross-attention. Subsequently, the model converts the fused features into sign language pose sequences through T-round denoising steps. During the training process, the model uses the ground-truth labels of sign poses as the starting point, generates Gaussian noise through T rounds of noise, and then performs T rounds of denoising to approximate the real sign language gestures. The entire process is constrained by the MAE loss function to ensure that the generated sign language gestures are as close as possible to the real labels. In the inference phase, the model directly randomly samples a set of Gaussian noise, generates multiple sign language gesture sequence hypotheses under the guidance of the gloss sequence, and outputs a high-confidence sign language gesture video by averaging multiple hypotheses. Experimental results on the Phoenix2014T dataset show that the proposed GCDM method achieves competitiveness in both quantitative performance and qualitative visualization. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Forming

来源：评论

学校读者我要写书评

暂无评论

Overview and New Opportunities for Multi-Source data Assimilation

引用

Journal of Meteorological Research 2025年第1期39卷 1-25页

作者： Xiaolei ZOU Joint Center of Data Assimilation for Research and Application Nanjing University of Information Science&TechnologyNanjing210044China

The world witnessed an accelerated development of various types of meteorological observing technology,an evolution of numerical weather prediction(NWP)models from single atmospheric component to coupled multi-components of the earth system,as well as the multi graphics processing unit technology in computer sciences,a new era for rapidly advancing data assimilation science and technology development has *** multi-source data assimilation is important not only for NWP but also for further understanding of global and regional weather *** article firstly selectively reviews past methods of multi-source data *** opportunities are then discussed for future development of data assimilation system framework,for innovative uses of high-resolution observations,and for applications of artificial intelligence machine learning in meteorological data assimilation.

关键词： multi-source observations data assimilation innovative use of high-resolution observations

来源：评论

学校读者我要写书评

暂无评论

Stylometry-driven framework for Urdu intrinsic plagiarism detection: a comprehensive analysis using machine learning, deep learning, and large language models

引用

Neural Computing and Applications 2025年第9期37卷 6479-6513页

作者： Manzoor, Muhammad Faraz Farooq, Muhammad Shoaib Abid, Adnan Department of Computer Science University of Management and Technology Lahore Pakistan Department of Data Science Faculty of Computing and Information Technology University of the Punjab Lahore Pakistan

Detecting plagiarism in documents is a well-established task in natural language processing (NLP). Broadly, plagiarism detection is categorized into two types (1) intrinsic: to check the whole document or all the passages have been written by a single author;(2) extrinsic: where a suspicious document is compared with a given set of source documents to figure out sentences or phrases which appear in both documents. In the pursuit of advancing intrinsic plagiarism detection, this study addresses the critical challenge of intrinsic plagiarism detection in Urdu texts, a language with limited resources for comprehensive language models. Acknowledging the absence of sophisticated large language models (LLMs) tailored for Urdu language, this study explores the application of various machine learning, deep learning, and language models in a novel framework. A set of 43 stylometry features at six granularity levels was meticulously curated, capturing linguistic patterns indicative of plagiarism. The selected models include traditional machine learning approaches such as logistic regression, decision trees, SVM, KNN, Naive Bayes, gradient boosting and voting classifier, deep learning approaches: GRU, BiLSTM, CNN, LSTM, MLP, and large language models: BERT and GPT-2. This research systematically categorizes these features and evaluates their effectiveness, addressing the inherent challenges posed by the limited availability of Urdu-specific language models. Two distinct experiments were conducted to evaluate the impact of the proposed features on classification accuracy. In experiment one, the entire dataset was utilized for classification into intrinsic plagiarized and non-plagiarized documents. Experiment two categorized the dataset into three types based on topics: moral lessons, national celebrities, and national events. Both experiments are thoroughly evaluated through, a fivefold cross-validation analysis. The results show that the random forest classifier achieved an ex

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Towards Optimization and Assessment of the Chinese New-generation VLBI Network for Earth Orientation Parameters Monitoring

引用

Research in Astronomy and Astrophysics 2025年第2期25卷 256-268页

作者： Hao Xiang Zhong-Kai Zhang Lan Du Ze-Jun Liu Xu-Qiao Wang College of Geospatial Information Information Engineering University Henan Industrial Technology Academy of Spatio-Temporal Big Data College of Geography and Environmental Science Henan University

The Earth Orientation Parameters(EOP) provide a time-varying transition relationship between the International Terrestrial Reference Frame and the International Celestial Reference Frame. To support deep space exploration and the Beidou Navigation Satellite System, the Chinese New-generation Very Long Baseline Interferometry Network(CNVN) is under construction for independent monitoring of the EOP. This paper evaluates the performance of existing 4-antenna CNVN through a batch generated observation schedules followed by extensive Monte Carlo simulations. The optimal positions of the fifth and sixth antennas of CNVN are found from 24hypothetical antenna positions uniformly distributed in China. In this process, the weighted parameters are optimized, which not only reduce the possibility of large error of EOP estimation accuracy due to unreasonable combination, but also greatly reduce the calculation cost.

关键词： methods: analytical techniques: interferometric reference systems

来源：评论

学校读者我要写书评

暂无评论

Partial Label Learning with Noisy Labels

引用

Annals of data science 2025年第1期12卷 199-212页

作者： Zhao, Pan Tang, Long Pan, Zhigeng School of Artificial Intelligence Nanjing University of Information Science & Technology Nanjing210044 China Research Institute of Talent Big Data Nanjing University of Information Science & Technology Nanjing210044 China

Partial label learning (PLL) is a particular problem setting within weakly supervised learning. In PLL, each sample corresponds to a candidate label set in which only one label is true. However, in some practical application scenarios, the emergence of label noise can make some candidate sets lose their true labels, leading to a decline in model performance. In this work, a robust training strategy for PLL, derived from the joint training with co-regularization (JoCoR), is proposed to address this issue in PLL. Specifically, the proposed approach constructs two separate PLL models and a joint loss. The joint loss consists of not only two PLL losses but also a co-regularization term measuring the disagreement of the two models. By automatically selecting samples with small joint loss and using them to update the two models, our proposed approach is able to filter more and more suspected samples with noise candidate label sets. Gradually, the robustness of the PLL models to label noise strengthens due to the reduced disagreement of the two models. Experiments are conducted on two state-of-the-art PLL models using benchmark datasets under various noise levels. The results show that the proposed method can effectively stabilize the training process and reduce the model's overfitting to noisy candidate label sets. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Phase locked loops

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based trust management for data exchange in internet of vehicle network

引用

Multimedia Tools and Applications 2025年第8期84卷 4837-4855页

作者： Srivastava, Sandeep Agarwal, Deepshikha Chaurasia, Brijesh Kumar Adhikari, Mainak Computer Science Indian Institute of Information Technology UP Lucknow226002 India Information Technology Indian Institute of Information Technology UP Lucknow226002 India Computer Science Pranveer Singh Institute of Technology UP Kanpur208029 India School of Data Science Indian Institute of Science Education & Research Thiruvananthapuram India

Internet of Vehicles (IoV) integrates with various heterogeneous nodes, such as connected vehicles, roadside units, etc., which establishes a distributed network. Vehicles are managed nodes providing all the services required during inter-vehicular communication which makes it essential to use a trust management mechanism. Existing trust management systems are insufficient to address the emerging IoV needs of transparency, mobility, immutability, and scalability. Motivated by the need to address the outlined issues, Proposed additive increase and multiplicative decrease (AIMD) trust management model, to improve the quality of communication, as well as vehicle trustworthiness based on multiple inter-vehicular interactions. The proposed layered architecture helps to reduce overhead in terms of latency and average execution time compared to other trust management mechanism and avoid risk of single point of failure. The Proposed AIMD trust management is implemented on permissioned blockchain, where transactions in the IoV network are only managed by minor nodes which accumulate interactions and uses PBFT and AIMD mechanism to derive immutable reputation score securely and transparently. Simulation results show the AIMD trust mechanism using permissioned blockchain can manage the trust of vehicles efficiently by reducing the latency by 0.29 sec, increasing packet delivery ratio from 0.8 to 0.95, and significantly reduce transaction finality time. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

A data representation method using distance correlation

引用

Frontiers of Computer science 2025年第1期19卷 1-14页

作者： Xinyan LIANG Yuhua QIAN Qian GUO Keyin ZHENG Institute of Big Data Science and Industry Shanxi UniversityTaiyuan 030006China Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi UniversityTaiyuan 030006China School of Computer Science and Technology Taiyuan University of Science and TechnologyTaiyuan 030024China Shanxi Key Laboratory of Big Data Analysis and Parallel Computing Taiyuan University of Science and TechnologyTaiyuan 030024China

Association in-between features has been demonstrated to improve the representation ability of data. However, the original association data reconstruction method may face two issues: the dimension of reconstructed data is undoubtedly higher than that of original data, and adopted association measure method does not well balance effectiveness and efficiency. To address above two issues, this paper proposes a novel association-based representation improvement method, named as AssoRep. AssoRep first obtains the association between features via distance correlation method that has some advantages than Pearson’s correlation coefficient. Then an improved matrix is formed via stacking the association value of any two features. Next, an improved feature representation is obtained by aggregating the original feature with the enhancement matrix. Finally, the improved feature representation is mapped to a low-dimensional space via principal component analysis. The effectiveness of AssoRep is validated on 120 datasets and the fruits further prefect our previous work on the association data reconstruction.

关键词： association representation distance correlation classification

来源：评论

学校读者我要写书评

暂无评论

Toward Precise Quantification of Energy Expenditure in Wheelchair Users

引用

IEEE Access 2025年 13卷 72189-72201页

作者： Alam, Iftikhar Ali, Zulfiqar Khalid, Wassauf Ali, Gauhar ELAffendi, Mohammed City University of Science and Information Technology Department of Computer Science Peshawar25000 Pakistan Prince Sultan University EIAS Data Science and Blockchain Laboratory College of Computer and Information Sciences Riyadh11586 Saudi Arabia

Modern electronic devices like smart bands, smartwatches, smartphones, and treadmills are widely used to track exertion metrics, also called energy expenditure, such as step counts, running, time, and distance. However, these devices often fail to meet the needs of individuals with mobility impairments, such as wheelchair users, for whom such metrics are hard to evaluate. This research introduces a tailored model to track and quantify exertion data for manual wheelchair users. The existing Heart Intensity Metric (HIM), which relies on parameters such as heart rate, weight, age, and time (exercise duration), is adapted with a revised Activity Intensity Assessor (AIA). The model incorporates critical factors for wheelchair users, including heart rate, adjusted movement status (1 for movement and zero for no movement), and inclination status, with new parameters, such as Metabolic Equivalent of Task (MET), and wheelchair speed. The revised AIA is then adapted for the energy expenditure formula to calculate calorie-burning estimation specifically for manual wheelchair users. The revised approach minimizes false positives commonly produced by existing approaches for manual wheelchair users, especially in scenarios involving non-movement exercises like upper limb activities. Unlike prior models, the proposed AIA ensures precise energy expenditure calculations, even during stationary activities, and reflects a zero-calorie expenditure when no exercise occurs. Results are statistically verified and demonstrate that traditional formulas yield inaccurate calorie estimations for wheelchair users, while the revised model aligns better with physiological realities. This work provides a practical framework for designing electronic tools that effectively track energy expenditure/total energy (ET), also known as exertion efforts, and estimate calories burnt by manual wheelchair users. The scope of this study is limited to examining energy expenditure exclusively for manual wheelcha

关键词： Wheelchairs Heart rate Software Legged locomotion Monitoring Manuals Estimation Accuracy Hardware Adaptation models

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：