检索结果-内蒙古大学图书馆

International Conference on Computing and Machine Learning, CML 2024

作者： Jayashree, G. Dharshini, S. Madhu Priya Lokesh, D. Kumar, Mathan Santhiya, C. Department of Computer Science and Engineering Thiagarajar College of Engineering Thiruparankundram TamilNadu Madurai India

ISBN: (纸本)9789819778386

Accurate soil analysis is crucial for optimizing crop cultivation and management since soil quality and texture are so important in the agricultural industry. We have incorporated deep learning (DL) into agriculture for classifying different soil textures, to enable farmers to increase crop output. Convolutional Neural Networks (CNNs), a powerful DL framework, are used in our method to automatically recognize silts, stones, and other color categories by learning detailed patterns inside soil images. The implementation is leveraged in Keras, an advanced neural network interface that is powered by TensorFlow for model creation and training. We harnessed the power of the Image Generator library to efficiently manage the image dataset. We experimented with the evaluation of four CNN models: Baseline, Augment, Dropout, and Padding. The Baseline model achieved an accuracy of 82%. The Augment model, which incorporated image augmentation, delivered an accuracy of 78%, while the Dropout model, utilizing dropout layers, achieved 60%. Notably, the Padding model excelled, yielding an impressive accuracy of 90%. This study marks a significant stride in harnessing DL technology for the betterment of agriculture, offering farmers the tools they need to make informed decisions and enhance their crop yields sustainably. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficient Detection of Runways, Taxiways, and Aprons in Commercial Airports Using YOLOv8 and High-Resolution Satellite Imagery 3

Efficient Detection of Runways, Taxiways, and Aprons in Comm...

引用

3rd International Conference on Intelligent Systems, Advanced Computing, and Communication, ISACC 2025

作者： Panneerselvam, Ramesh Kumar Yasen Shaik, Mohammed Sundarapalli, Hanish Venkat Prakash Gandham, Kumar N S L Velagapudi Ramakrishna Siddhartha Engineering College Department of Computer Science and Engineering Vijayawada India

ISBN: (纸本)9798331523893

This study presents an advanced satellite-based detection system designed for the comprehensive identification of multiple facilities within both commercial and civilian airports. The system utilizes cutting-edge remote sensing technologies and machine learning algorithms to accurately detect and categorize various essential elements crucial for airport operations. These elements include runways, taxiways, and aprons. Using high-resolution satellite imagery, the system aims to improve airport infrastructure management, optimize safety protocols, and improve overall operational efficiency on a global scale. Leveraging deep learning techniques, specifically object detection models, we explore the suitability of different architectures such as Faster R-CNN, YoLO V8, detectors for accurately identifying these facilities. The project involves extensive data collection, preprocessing, model training, and evaluation to ensure robust performance. Considering the potential deployment on edge devices, the chosen models are optimized for efficiency without compromising accuracy. © 2025 IEEE.

关键词： Airport runways

来源：评论

学校读者我要写书评

暂无评论

An Intelligent and Dynamic Replication Scheme for Reliable Cloud Environment 3

An Intelligent and Dynamic Replication Scheme for Reliable C...

引用

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Damodhar, M. Rao, Ch.D.V. Subba Sri Venkateswara University College of Engineering Department of Computer Science and Engineering Tirupati India

ISBN: (纸本)9798331508456

Recently, cloud computing research, especially Virtual Machine based replication schemes and their applications, were becoming prevalent. A cloud data center (DC) comprises of hosts with an enormous of virtual machines (VMs) where determining replica quantity and replication order is a tedious task to minimize cost and bandwidth. Majority of the existing dynamic replication techniques rely on budget constraints and server failure rate to guarantee customer requirements. But, there is a strong need to determine replication order of servers to retain the performance and system stability. In this paper, we suggest two different algorithms for better selection with proper and intelligent placement of replicas in the cloud region. The proposed algorithms towards dynamic replication are request based replica selection (RRS) and ant colony optimization (ACO). The foremost proposed algorithm was request based replica selection used for obtaining the best selected replicas depends upon the VM performance ranking and failure probability based on the task requirement. Conversely, the subsequent offered algorithm is ACO that is helpful to find the best location to place the designated replica depends on the least-cost distance metric, and the replicas availability in order to encompass and regulate with the entire network load and the link bottlenecks. The performance of proposed techniques using CloudSim was evaluated against various pro-active fault tolerance strategies. The simulation results gives that dynamic replica selection provides efficient task replication when compared with the existing pro-active algorithms. Additionally, ACO realizes high availability, low cost, and less bandwidth utilization. © 2025 IEEE.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Multi-Model Deep Learning Framework for Plant Disease Detection and Classification using YOLOv5, Xception, and DenseNet

Multi-Model Deep Learning Framework for Plant Disease Detect...

引用

2025 International Conference on Visual Analytics and Data Visualization, ICVADV 2025

作者： Meshram, Kunal K. Khandelwal, Sarika Kumre, Jyoti G H Raisoni College of Engineering Department of Computer Science and Engineering Nagpur India

ISBN: (纸本)9798331521394

Plant diseases lead to food loss and yield reduction, which is a serious challenge to food security globally. Researchers have suggested deep learning models, which are trained using plant disease data like PlantVillage and PlantDoc, as a means of solving this issue. The traditional solutions usually do not work under practical agricultural environments. This research combines machine learning (ML) models and image processing methods for agricultural use. This study utilizes the algorithms, such as MobileNet, VGG16, YOLOv8, and Faster R-CNN, to upgrade plant disease identification and classification. Our method utilizes deep learning architectures for both object detection and plant disease classification. We offer real-time crop analysis to help farmers make informed decisions, achieve maximum productivity, and enhance sustainable agriculture. Leveraging previous work, we seek to enhance performance through DenseNet and Xception for classification and YOLOv5 for object detection. We also use a Flask-based, easy-to-use front-end for authentication-based client testing. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Traffic flow prediction based on graph convolutional networks with a parallel attention network and stacked gate recurrent units

引用

Multimedia Tools and Applications 2025年第15期84卷 14329-14358页

作者： Xia, Dawen Ao, Yuce Wei, Xiaoduo Li, Yunsong Chen, Yan Hu, Yang Li, Yantao Li, Huaqing College of Data Science and Information Engineering Guizhou Minzu University Guiyang550025 China Department of Automotive Engineering Guizhou Traffic Technician and Transportation College Guiyang550008 China College of Computer Science Chongqing University Chongqing400044 China College of Electronic and Information Engineering Southwest University Chongqing400715 China

Accurate traffic flow prediction is essential to address traffic issues and assist traffic managers make informed decisions in intelligent transportation systems. Extracting potential features from traffic data is challenging due to the complex topology of urban road networks and the time-varying traffic flow. To capture the global spatiotemporal characteristics of traffic flow, we propose a novel model based on graph convolutional networks with a parallel attention network and stacked gated recurrent units (PAGCN-SGRU). First, the parallel attention (PA) network enhances the feature representation of global traffic road nodes and road segments. Then, the graph convolutional networks (GCN) are designed to extract spatial characteristics. Next, the stacked gate recurrent units (SGRU) are employed to capture temporal features. Finally, PAGCN-SGRU discovers global spatiotemporal features for traffic flow prediction. The experimental results demonstrate that the accuracy of PAGCN-SGRU under the SZ-dataset is improved by 9.76%, 72.54%, 5.76%, 16.07%, 2.07%, 1.82%, 3.35%, and 6.59%, respectively, compared to that of HA, ARIMA, SVR, GCN, T-GCN, A3T-GCN, ST-GCN, and DCRNN. In the Los-dataset, the accuracy values increase by 7.11%, 8.94%, 6.66%, 7.77%, 3.43%, 2.45%, 2.28%, and 4.09%, respectively. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Signbridge-Audio to Sign Language Translator

Signbridge-Audio to Sign Language Translator

引用

2025 IEEE International Students' Conference on Electrical, Electronics and computer science, SCEECS 2025

作者： Shirisha, Kammadanam Deeksith, E. Mani Madhava, M. S. S Sri Surendhar, S. Karthikeyan, R. Vardhaman College of Engineering Department of Computer Science and Engineering Hyderabad India Hyderabad India

ISBN: (纸本)9798331529833

The lack of communication options for Deaf and hearing people, some may say creates a significant social disadvantage in accessing the often-bare essential services. In contrast to acoustically communicated sound patterns, sign language communicates ideas freely through manual and body language. It can be used by those who have trouble speaking, by those who can hear but cannot talk, and by regular people to interact with those with hearing impairments. By automatically converting spoken words into hand gestures, this project creates a web-based interface that allows hearing-impaired individuals to communicate with normal people in real time through sign language interpretation. Two major phases of the system Speech-to-text technology interprets oral input into textual output. Next, the text is run through Natural Language Processing (NLP) algorithms leveraging the Natural language toolkit (NLTK) to be syntactically parsed in the context of sign natural rules. The last phase translates the parsed text into sign language gestures which involve hand shapes, orientation, and body movements to convey the visual meaning of a message. This system could be used to greatly reduce the communication barriers experienced by people with hearing loss and deafness using Machine Learning (ML) to continuously improve accuracy, enhance quality of life, and provide a more inclusive society between the deaf community in our daily interactions within an ever-growing world. © 2025 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

A hierarchical byzantine fault tolerance consensus protocol for the Internet of Things

引用

High-Confidence Computing 2024年第3期4卷 13-24页

作者： Rongxin Guo Zhenping Guo Zerui Lin Wenxian Jiang College of Engineering Huaqiao UniversityQuanzhou 362000China College of Computer Science and Technology Huaqiao UniversityXiamen 361021China

The inefficiency of Consensus protocols is a significant impediment to blockchain and IoT convergence *** solve the problems like inefficiency and poor dynamics of the Practical Byzantine Fault Tolerance(PBFT)in IoT scenarios,a hierarchical consensus protocol called DCBFT is *** all,we propose an improved k-sums algorithm to build a two-level consensus cluster,achieving an hierarchical management for IoT ***,A scalable two-level consensus protocol is proposed,which uses a multi-primary node mechanism to solve the single-point-of-failure *** addition,a data synchronization process is introduced to ensure the consistency of block data after view ***,A dynamic reputation evaluation model is introduced to update the nodes’reputation values and complete the rotation of consensus nodes at the end of each consensus *** experimental results show that DCBFT has a more robust dynamic and higher consensus ***,After running for some time,the performance of DCBFT shows some improvement.

关键词： IoT Hierarchical consensus Clustering Reputation evaluation model Practical byzantine fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Impact of UAV-Based Transmitter Mobility on Physical Layer Security

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 5604-5619页

作者： Ruby, Rukhsana Elhalawany, Basem M. Pham, Quoc-Viet Wu, Kaishun Wang, Lu Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China Kuwait College of Science and Technology Electronics and Communication Engineering department Block 4 Doha District93004 Kuwait Trinity College School of Computer Science and Statistics Dublin 2 DublinD02 PN40 Ireland

Owing to flexible management and low overhead, wireless physical layer security (PLS) has been applied to support many critical applications (e.g., data dissemination) of unmanned aerial vehicles (UAVs)-based mobile communication networks in emergency scenarios. Although the impact of static network scenarios or receiver mobility on PLS has been well studied, there is no much work that studies the impact of UAV-based transmitter mobility on PLS. To fill this gap, in this paper, we investigate PLS of a scenario, where a random mobile UAV-based transmitter transmits information to a static ground entity under Rayleigh fading channel. More specifically, we consider a communication system, in which a mobile UAV hovers over a region to collect information and then disseminates this information to a static ground network entity in a confidential manner under the presence of an eavesdropper. Because of popularity and practicality, the UAV is assumed to hover following the random way point (RWP) mobility model. We investigate the secrecy characteristics of the UAV under steady running state in terms of ergodic secrecy capacity (ESC), positive secrecy capacity probability (PSCP) and secrecy outage probability (SOP) for the communication between the UAV and the receiver. We then investigate the secrecy performance of the proposed system while considering the pause time of the RWP mobility model adopted by the UAV. We further extend our proposed theoretical model to other realistic scenarios, including the presence of multiple cooperative and non-cooperative eavesdroppers, and study the PSCP and SOP metrics of the corresponding system. Furthermore, we propose three types of secrecy improvement strategies for the considered communication model. We strike a good trade-off between the secrecy improvement and transmit outage probability. Extensive simulations have been conducted to validate our theoretical analysis as well as the effectiveness of the proposed secrecy improvement s

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

3D Road Network Modeling and Road Structure Recognition in Internet of Vehicles

引用

computer Modeling in engineering & sciences 2024年第2期138卷 1365-1384页

作者： Dun Cao Jia Ru Jian Qin Amr Tolba Jin Wang Min Zhu College of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China Department of Computer Science Community CollegeKing Saud UniversityRiyadh11437Saudi Arabia College of Information Science and Technology Zhejiang Shuren UniversityHangzhou310015China

Internet of Vehicles (IoV) is a new system that enables individual vehicles to connect with nearby vehicles,people, transportation infrastructure, and networks, thereby realizing amore intelligent and efficient transportationsystem. The movement of vehicles and the three-dimensional (3D) nature of the road network cause the topologicalstructure of IoV to have the high space and time *** modeling and structure recognition for 3Droads can benefit the description of topological changes for IoV. This paper proposes a 3Dgeneral roadmodel basedon discrete points of roads obtained from GIS. First, the constraints imposed by 3D roads on moving vehicles areanalyzed. Then the effects of road curvature radius (Ra), longitudinal slope (Slo), and length (Len) on speed andacceleration are studied. Finally, a general 3D road network model based on road section features is *** paper also presents intersection and road section recognition methods based on the structural features ofthe 3D road network model and the road features. Real GIS data from a specific region of Beijing is adopted tocreate the simulation scenario, and the simulation results validate the general 3D road network model and therecognitionmethod. Therefore, thiswork makes contributions to the field of intelligent transportation by providinga comprehensive approach tomodeling the 3Droad network and its topological changes in achieving efficient trafficflowand improved road safety.

关键词： Internet of vehicles road networks 3D road model structure recognition GIS

来源：评论

学校读者我要写书评

暂无评论

SmartFood AI: A Multimodal Framework for Accessible Nutritional Analysis

SmartFood AI: A Multimodal Framework for Accessible Nutritio...

引用

2025 International Conference on Artificial Intelligence and Data engineering, AIDE 2025

作者： Steffy Sherly, P. Velvizhy, P. Navanitha Krishnan, N. Matan, P. Anna University College of Engineering Guindy Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331527518

This work presents an advanced food detection system leveraging computer vision and AI to enhance food recognition and nutritional analysis, aligning with global health goals set by organizations like World Health Organization (WHO) and the Food and Agriculture Organization (FAO). These organizations emphasize the critical role of nutrition in public health and advocate for accessible, accurate dietary information to combat malnutrition and promote balanced diets. Powered by a deep learning based framework, the proposed system delivers high-precision food identification through a bounding box regressor for localization and a knowledge graph for nutritional insights. Its zero-shot learning capability enables recognition of previously unseen foods without additional training, addressing the limitations of traditional systems by providing accurate identification alongside contextual nutritional data. This adaptability allows the system to evolve with changing dietary trends and meet diverse user needs, supporting applications in healthcare, personal nutrition monitoring, and food. Moreover;It is beneficial for visually impaired individuals, enhancing autonomy by enabling them to recognize foods and access essential nutritional information independently, thereby promoting healthier living. The system demonstrates robust performance across varied conditions, making it effective for both personal use and public health applications. By providing critical dietary insights and adapting to new foods, this AI-powered solution represents a scalable and impactful tool in computer vision and dietary *** promotes global health initiatives and personal well-being by providing a useful strategy for raising awareness of nutrition and encouraging better lifestyles. © 2025 IEEE.

关键词： Nutrition

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：