检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Parsa, Antara Firoz Abdullah, S.M. Talukder, Anika Hasan Kabbya, Md Asif Shahidullah Hasan, Shakib Al Islam, Md Farhadul Noor, Jannatun Department of Computer Science and Engineering School of Data and Sciences BRAC University Dhaka Bangladesh Research Group Department of Computer Science and Engineering United International University Dhaka Bangladesh

The study involves a comprehensive performance analysis of popular classification and segmentation models, applied over a Bangladeshi pothole dataset, being developed by the authors of this research. This custom dataset of 824 samples, collected from the streets of Dhaka and Bogura performs competitively against the existing industrial and custom datasets utilized in the present literature. The dataset was further augmented four-fold for segmentation and ten-fold for classification evaluation. We tested nine classification models (CCT, CNN, INN, Swin Transformer, ConvMixer, VGG16, ResNet50, DenseNet201, and Xception) and four segmentation models (U-Net, ResU-Net, U-Net++, and Attention-Unet) over both the datasets. Among the classification models, lightweight models namely CCT, CNN, INN, Swin Transformer, and ConvMixer were emphasized due to their low computational requirements and faster prediction times. The lightweight models performed respectfully, oftentimes equating to the performance of heavyweight models. In addition, augmentation was found to enhance the performance of all the tested models. The experimental results exhibit that, our dataset performs on par or outperforms the similar classification models utilized in the existing literature, reaching accuracy and f1-scores over 99%. The dataset also performed on par with the existing datasets for segmentation, achieving model Dice Similarity Coefficient up to 67.54% and IoU scores up to 59.39%. © 2025, CC BY-NC-SA.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Motion Planning in Automated Vehicles Based on Hierarchical MPC 1

Motion Planning in Automated Vehicles Based on Hierarchical ...

引用

1st International Conference on Advances in computer Science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Kapila, Pooja Kumar, Pankaj Negi, Rahul Bharti, Bhupender Kumar Punhani, Akash Bisht, Suraj Singh IIMT College of Engineering Department of Artifical Intelligence & Data Science India Amity University Department of Statistics Kolkata India Tula's Institute Department of ECE Dehradun248197 India Department of Mechanical Engineering VMSB UTU Campus Pithoragarh India KIET Group of Institutions Department of Computer Science Noida India Bipin Tripathi Kumaon Institute of Technology Department of ECE Dwarahat Almora India

ISBN: (纸本)9798331518578

In this study, a thorough hierarchical control structure that supports autonomous decision-making that arises in autonomous systems and robots is proposed. Distinct state and decision/control sets are frequently used to describe high-level decision making in a conventional hierarchical control architecture. To keep up with proficiency, wellbeing, and solace, robotized vehicles generally depend serious areas of strength for on powerful movement arranging calculations. The capacity of Model Prescient Control (MPC) to oversee imperatives and upgrade directions progressively has made it a strong system for movement arranging. To approve the proposed strategy, this exploration utilizes MATLAB recreations to look at various levelled MPC for movement arranging in robotized vehicles. With the low-level regulator guaranteeing exact direction observing and the undeniable level organizer computing a worldwide direction, a two-layer progressive MPC structure is fabricated. The discoveries show how well the progressive MPC handles street ebb and flow, dynamic hindrances, and continuous computational impediments. It is demonstrated that the suggested autonomous decision-making scheme's recursive practicality and stability are ensured by carefully crafting its essential components. An intelligent vehicle's autonomous lane-changing system is developed using the suggested framework. Simulation demonstrates that it has a potential capacity to manage a variety of behaviours in complex and dynamic contexts. It is anticipated that the suggested framework will be useful for autonomous decision-making in a variety of robotics along with autonomous technologies where safety as well as optimality are important factors. © 2025 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Monkeypox Disease Classification from Skin Lesion Images using Deep Convolution Neural Network

Monkeypox Disease Classification from Skin Lesion Images usi...

引用

International Symposium on Advanced Computing and Communication (ISACC)

作者： Rajasekaran Thangaraj Balasubramaniam Vadivel S. Manoj Kumar S. Sadesh P Karunakaran Prakash P Department of Computer Science and Engineering Nandha Engineering College Erode India Department of Computer Science and Engineering Sri Ramakrishna Institute of Technology Coimbatore India Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore India Department of Artificial Intelligence and Data Science Velalar College of Engineering and Technology Erode India Department of Artificial Intelligence and Data Science Nandha Engineering College Erode India Department of Information Technology Velalar College of Engineering and Technology Erode India

ISBN: (数字)9798331523893

ISBN: (纸本)9798331523909

Recently monkeypox outbreak has raised concerns due to its increasing number of cases and diverse dermatological symptoms in 2024, which can complicate early diagnosis due to similarities with other viral infections such as measles and chickenpox. To enhance diagnostic accuracy, transfer learning models and artificial intelligence (AI) have been explored as effective tools. Pre-trained models such as VGG16, VGG19, ResNet50V2, and MobileNetV2 have been employed for monkeypox detection, each with distinct trade-offs in terms of computational efficiency and diagnostic precision. MobileNetV2 offers superior efficiency, but this comes at the cost of reduced accuracy. VGG models provide higher accuracy but require much more computational *** these models, DenseNet121 stands out by achieving 99% accuracy while requiring 37% less computational power, making it the model optimized choice for efficient and accurate monkeypox classification.

关键词： Deep learning Accuracy Computational modeling Surveillance Transfer learning Neural networks Measles Skin Computational efficiency Reliability

来源：评论

学校读者我要写书评

暂无评论

FedNorm: Optimised Federated Learning Strategy Using Hybrid Regularisation Norm 12th

FedNorm: Optimised Federated Learning Strategy Using Hybrid ...

引用

12th International Conference on Big data and Artificial Intelligence, BDA 2024

作者： John, Binu Menon, Varun Adhikari, Mainak Department of Computer Science and Engineering SCMS School of Engineering and Technology Kerala Ernakulam683576 India APJ Abdul Kalam Technological University Kerala Thiruvananthapuram695016 India School of Data Science Indian Institute of Science Education and Research Vithura Kerala Thiruvananthapuram695551 India

ISBN: (纸本)9783031818202

Federated Learning (FL) has emerged as a game-changing method for training machine learning (ML) models on decentralized data sources without centralizing the data itself. Conventional FL algorithms frequently exhibit performance instability and inefficiency, especially when working with non-Independent and Identically Distributed (non-IID) data distributions. To overcome these difficulties, we present FedNorm, a new FL method that uses hybrid regularisation approach to improve model stability and accuracy by balancing sparsity and smoothness, to increase generalization across varied data distributions. Our experimental setup uses the MNIST dataset to train models in both Independent and Identically Distributed (IID) and non-IID situations. The findings show that FedNorm routinely outperforms classic algorithms like FedAvg, FedSGD, FedNova and FedSAM, with minimal test loss and high accuracy. FedNorm has an exceptional accuracy rating of 0.98 on both IID and non-IID data. FedNorm addresses the constraints of conventional FL algorithms, resulting in a strong and dependable solution for FL in diverse situations. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Strategies for Multiclass Skin Disease Classification 5th

Deep Learning Strategies for Multiclass Skin Disease Classi...

引用

5th EAI International Conference on Cognitive Computing and Cyber Physical Systems, IC4S 2024

作者： Venkat, Nakka Lokeswara Satya Tejasri, Masina Naga Vijaya Uppalapati, Padma Jyothi Rao, V. V. R. Maheswara Sripada, V. S. S. Lakshmi Murty, P. Sita Rama Department of Artificial Intelligence and Data Science Vishnu Institute of Technology Andhra Pradesh Bhimavaram534201 India Department of Computer Science and Engineering Vishnu Institute of Technology Andhra Pradesh Bhimavaram534201 India Department of CSE Shri Vishnu Engineering College for Women Andhra Pradesh Bhimavaram534201 India Andhra Pradesh Bhimavaram534201 India

ISBN: (纸本)9783031770746

Skin diseases represent a significant global health challenge, necessitating accurate and timely diagnosis for effective treatment. In this paper, we delve into the intricate realm of skin disease classification, leveraging advanced deep learning techniques. Skin diseases, ranging from common conditions like eczema and atopic dermatitis to potentially life-threatening melanoma, pose complex diagnostic challenges due to their varied visual characteristics. Accurate classification demands the ability to discern subtle patterns, textures, and features within medical images. Our paper introduces a novel methodology that includes the integration of our proposed model into the existing deep learning frameworks. Unlike conventional approaches involving the replacement of output layers, our model maintains the integrity of pre-trained structures. It achieves this by utilizing a blend of VGG16 and EfficientNet B2, incorporating dense activations for improved regularization. This novel approach seeks to improve the model’s flexibility to various skin disease patterns while maintaining accurate classification without changing the pre-trained models’ fundamental design. The model’s performance is evaluated in-depth using a variety of criteria, including accuracy, precision, recall, and F1 score. The outcomes of this analysis unveil distinct F1 scores for each disease class across different models, thereby illuminating the models’ strengths and limitations in the context of disease classification. © ICST Institute for computer Sciences, Social Informatics and Telecommunications engineering 2025.

关键词： Dermatitis

来源：评论

学校读者我要写书评

暂无评论

GeoAgriGuard: AI-Driven Pest and Disease Management with Remote Sensing for Global Food Security

引用

Remote Sensing in Earth Systems Sciences 2025年第2期8卷 409-422页

作者： Sharada, K. Choudhary, Shailee Lohmor Harikrishna, T. Dixit, Rinku Sharma Suman, Sanjay Kumar Ayyappa Chakravarthi, M. Bhagyalakshmi, L. Department of Computer Science and Engineering GITAM (Deemed to Be University) AP Visakhapatnam India Department of Artificial Intelligence and Machine Learning New Delhi Institute of Management Delhi India Department of AIML Annamacharya University Andhra Pradesh Rajampet India Department of ECE St. Martin’s Engineering College Telangana Secunderabad India Departmentt of CSE-Data Science KSR Institute of Technology and Science KKR & AP Guntur India Department of ECE Rajalakshmi Engineering College TN Chennai India

Agricultural productivity is increasingly threatened by the growing frequency and severity of pest and disease outbreaks, exacerbated by climate change and evolving environmental conditions. The GeoAgriGuard AI-Driven Pest and Disease Management System integrates remote sensing technologies with advanced AI models to address pest and disease outbreaks in agriculture. Utilizing multi-spectral and hyper-spectral satellite and drone imagery, the system processes crop health data through comprehensive preprocessing steps, including radiometric, geometric, and atmospheric corrections. Vegetation indices such as NDVI and NDWI further enhance the data quality, ensuring accurate detection of crop stress. A hybrid deep learning ensemble, combining models like ResNet, Transformer, DenseNet, and AutoEncoders, processes this data to predict and classify pest and disease occurrences. The proposed model achieved a remarkable accuracy of 97.81%, significantly outperforming existing models such as SVM (82.45%) and CNN (90.12%). By integrating these AI predictions with GIS-based spatial analysis, the system generates real-time risk maps, enabling farmers to take timely and localized actions. Performance metrics, including precision (96.72%), recall (95.83%), and F1-score (96.27%), demonstrate the system’s reliability in real-world applications. GeoAgriGuard provides a scalable, data-driven solution for enhancing crop protection and improving global food security. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： AI-driven agriculture Crop disease Deep learning Food security GIS NDVI Pest detection Precision agriculture Remote sensing Satellite imagery

来源：评论

学校读者我要写书评

暂无评论

Convergence-Privacy-Fairness Trade-Off in Personalized Federated Learning

IEEE Transactions on Machine Learning in Communications and ...

引用

IEEE Transactions on Machine Learning in Communications and Networking 2025年 3卷 246-262页

作者： Zhao, Xiyu Cui, Qimei Li, Weicai Ni, Wei Hossain, Ekram Sheng, Quan Z. Tao, Xiaofeng Zhang, Ping School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China School of Computing Macquarie University SydneyNSW2109 Australia Department of Broadband Communication Peng Cheng Laboratory Shenzhen518055 China School of Electrical and Data Engineering University of Technology Sydney SydneyNSW2007 Australia Department of Electrical and Computer Engineering University of Manitoba WinnipegMBR3T 2N2 Canada

Personalized federated learning (PFL), e.g., the renowned Ditto, strikes a balance between personalization and generalization by conducting federated learning (FL) to guide personalized learning (PL). While FL is unaffected by personalized model training, in Ditto, PL depends on the outcome of the FL. However, the clients’ concern about their privacy and consequent perturbation of their local models can affect the convergence and (performance) fairness of PL. This paper presents PFL, called DP-Ditto, which is a non-trivial extension of Ditto under the protection of differential privacy (DP), and analyzes the trade-off among its privacy guarantee, model convergence, and performance distribution fairness. We also analyze the convergence upper bound of the personalized models under DP-Ditto and derive the optimal number of global aggregations given a privacy budget. Further, we analyze the performance fairness of the personalized models, and reveal the feasibility of optimizing DP-Ditto jointly for convergence and fairness. Experiments validate our analysis and demonstrate that DP-Ditto can surpass the DP-perturbed versions of the state-of-the-art PFL models, such as FedAMP, pFedMe, APPLE, and FedALA, by over 32.71% in fairness and 9.66% in accuracy. © 2023 CCBY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Digital Twin-based Dynamic Resource Provisioning Using Deep Q-Network on 6G-enabled Mobile Edge Networks 17

Digital Twin-based Dynamic Resource Provisioning Using Deep ...

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Alex, Suja A. Singh, Neha Adhikari, Mainak St. Xavier's Catholic College of Engineering Department of Information Technology Nagercoil India Indian Institute of Information Technology Lucknow Department of Computer Science Lucknow India Indian Institute of Science Education and Research Thiruvananthapuram School of Data Science Thiruvananthapuram India

ISBN: (纸本)9798331531195

The advancement of Digital Twin (DT) technology has enabled the creation of digital replicas of physical entitics, significantly enhancing the functionality and performance of mobile networks. However, this innovative approach also introduces considerable overload and performance challenges for mobile edge networks. To address these issucs, we propose a novel DT-enabled edge architecture for 6G-capable technology, employing a dynamic resource allocation strategy. The proposed approach, termed DT-based Dynamic Resource Provisioning (DT-DRP), leverages the capabilities of DT technology and Decp Reinforcement Learning (DRL) to dynamically allocate incoming tasks from mobile devices to edge devices. An intelligent DT server facilitates this allocation, optimizing resource use and improving network performance. The predictive capabilities of the framework are validated using the K-Nearest Neighbor (KNN) dlassifier at the edge network. Experimental results demonstrate that the proposed DT-DRP framework incorporates mobile devices into the DT network scamlessly, achieving superior performance in terms of minimum latency and high accuracy compared to bascline Q-learning algorithms across two medical datasets and various exccution scenarios. This research underscores the potential of DT technology in 6G networks and highlights its efficacy in enhancing mobile edge computing performance through intelligent resource management. © 2025 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Efficiency of the Grouping-Scoring-Modeling Framework with Statistical Pre-Scoring Component for Transcriptomic data Analysis

Enhancing the Efficiency of the Grouping-Scoring-Modeling Fr...

引用

18th International Joint Conference on Biomedical engineering Systems and Technologies, BIOSTEC 2025

作者： Khokhar, Maham Bakir-Gungor, Burcu Yousef, Malik Department of Data Science Social Sciences Institute Abdullah Gul University Kayseri38080 Turkey Department of Computer Engineering Faculty of Engineering Abdullah Gul University Kayseri38080 Turkey Department of Information Systems Galilee Digital Health Research Center Zefat Academic College Zefat13206 Israel

The advent of high-throughput transcriptomic technologies has generated vast transcriptomic datasets, challenging current analytical methodologies with their sheer volume and complexity. The Grouping-Scoring Modeling (G-S-M) approach is one of the recent approaches that treat groups of genes (or clusters of genes) by embedding prior biological knowledge with machine learning in order to detect the most significant groups for classification tasks. The G-S-M might need to treat thousand ten thousand of groups (scoring those groups) which might affect the speed and performance of the algorithm. In response, this study introduces the Pre Scoring G-S-M model, an enhancement of the established Grouping-Scoring-Modeling (G-S-M) framework. This approach incorporates a Pre-Scoring component that leverages the Limma package for its empirical Bayes methods to optimize initial transcriptomic data evaluation through a percentage-based selection of statistically significant gene groups. Aimed at reducing computational demand and streamlining feature selection, the model also addresses data redundancy by eliminating duplicate gene-disease associations. Application to nine human gene expression datasets from the GEO database showed promising results. It demonstrated improvements in computational efficiency and analytical precision while reducing the number of features selected per dataset compared to the traditional G-S-M approach, without compromising accuracy. These initial findings highlight the Pre-Scoring G-S-M model's potential to enhance transcriptomic data analysis, indicating a promising direction for future bioinformatics research. © 2025 by SCITEPRESS– Science and Technology Publications, Lda.

关键词： data accuracy

来源：评论

学校读者我要写书评

暂无评论

MTMD: Multi-Scale Temporal Memory Learning and Efficient Debiasing Framework for Stock Trend Forecasting

引用

IEEE Transactions on Emerging Topics in Computational Intelligence 2025年第3期9卷 2151-2163页

作者： Wang, Mingjie Tian, Juanxi Zhang, Mingze Guo, Jianxiong Jia, Weijia BNU-HKBU United International College Guangdong Key Lab of Ai and Multi-Modal Data Processing Department of Computer Science Zhuhai519087 China Gonzaga University School of Engineering and Applied Sciences SpokaneWA99258 United States Beijing Normal University Advanced Institute of Natural Sciences Zhuhai519087 China BNU-HKBU United International College Guangdong Key Lab of Ai and Multi-Modal Data Processing Zhuhai519087 China

The endeavor of stock trend forecasting is principally focused on predicting the future trajectory of the stock market, utilizing either manual or technical methodologies to optimize profitability. Recent advancements in machine learning technologies have showcased their efficacy in discerning authentic profit signals within the realm of stock trend forecasting, predominantly employing temporal data derived from historical stock price patterns. Nevertheless, the inherently volatile and dynamic characteristics of the stock market render the learning and capture of multi-scale temporal dependencies and stable trading opportunities a formidable challenge. This predicament is primarily attributed to the difficulty in distinguishing real profit signal patterns amidst a plethora of mixed, noisy data. In response to these complexities, we propose a Multi-Scale Temporal Memory Learning and Efficient Debiasing (MTMD) model. This innovative approach encompasses the creation of a learnable embedding coupled with external attention, serving as a memory module through self-similarity. It aims to mitigate noise interference and bolster temporal consistency within the model. The MTMD model adeptly amalgamates comprehensive local data at each timestamp while concurrently focusing on salient historical patterns on a global scale. Furthermore, the incorporation of a graph network, tailored to assimilate global and local information, facilitates the adaptive fusion of heterogeneous multi-scale data. Rigorous ablation studies and experimental evaluations affirm that the MTMD model surpasses contemporary state-of-the-art methodologies by a substantial margin in benchmark datasets. © 2025 IEEE.

关键词： Profitability

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：