检索结果-内蒙古大学图书馆

Random hyperbolic graphs in d+1 dimensions

Physical Review E 2024年第5期109卷 054131-054131页

作者： Gabriel Budel Maksim Kitsak Rodrigo Aldecoa Konstantin Zuev Dmitri Krioukov Faculty of Electrical Engineering Mathematics and Computer Science Department of Physics Network Science Institute Department of Computing and Mathematical Sciences Department of Physics Department of Mathematics Department of Electrical & Computer Engineering

We consider random hyperbolic graphs in hyperbolic spaces of any dimension d+1≥2. We present a rescaling of model parameters that casts the random hyperbolic graph model of any dimension to a unified mathematical framework, leaving the degree distribution invariant with respect to the dimension. Unlike the degree distribution, clustering does depend on the dimension, decreasing to 0 at d→∞. We analyze all of the other limiting regimes of the model, and we release a software package that generates random hyperbolic graphs and their limits in hyperbolic spaces of any dimension.

关键词： Network formation & growth Network structure

来源：评论

学校读者我要写书评

暂无评论

Pneumonia Detection in Chest X-Rays Using Combined Approach of Deep Learning 2

Pneumonia Detection in Chest X-Rays Using Combined Approach ...

引用

2nd IEEE International Conference on Networks, Multimedia and Information Technology, NMITCON 2024

作者： Aditya Pai, H. Pareek, Piyush Kumar Guruprasad, M.S. Chandrappa, S. Bhargava, Krishna Mit Art Design and Technology University Mit School of Computing Pune India Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India Department of Computer Science and Engineering Dehradun India School of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350372892

A respiratory infection like pneumonia faces a serious health challenge across the globe, especially in the poor and underdeveloped countries. The pneumonia is affected by various factors like bacteria or viruses. The reason for the affection is due to higher level of pollution, poor air quality, excess of population, poor infrastructure etc. To reduce the threat from pneumonia, there is a need for early and accurate detection of the infection by using chest X-ray images as the most effective diagnostic method. The paper proposes an automated chest X-ray analysis system by using VGG16 architecture and a weighted average ensemble method to enhance diagnostic accuracy. By integrating deep transfer learning, the system overcomes data scarcity issues, achieving a remarkable 99% accuracy on a publicly available dataset. The research underscores the potential of automated systems in improving pneumonia diagnosis, highlighting the urgent need for advanced diagnostics in resource-limited settings. © 2024 IEEE.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

Polar Region Climate Dynamics: Deep Learning and Remote Sensing Integration for Monitoring Arctic and Antarctic Changes

引用

Remote Sensing in Earth Systems sciences 2024年第4期7卷 582-595页

作者： Maniraj, Subramanian Pitchiah Rose, Jesuharan Dafni Arunachalam, Rohini Rangasamy, Kotteeswaran Patil, Vishal Ratansing Kathirvelu, Selvakumarasamy Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulathur Campus Chennai India Department of Computer Science and Engineering St. Joseph’s Institute of Technology Chennai India Department of Computer Science and Engineering Anil Neerukonda Institute of Technology and Sciences Andhra Pradesh Visakhapatnam India Joseph’s College of Engineering Chennai 600119 India Department of CSE(AIML) Vishwakarma Institute of Technology Pune India Department of Electronics and Communication Engineering Saveetha School of Engineering (SIMATS) Chennai India

The polar regions of the Earth, specifically the Arctic and Antarctic, play a pivotal role in regulating the planet’s climate systems. These regions are highly sensitive to climate change, with observable shifts such as diminishing sea ice, retreating glaciers, and rising temperatures. Understanding these dynamics is essential for predicting broader global climate impacts. This paper presents a novel approach for monitoring and predicting these changes by integrating an attention-based transformer model with a 3D convolutional neural network (3D-CNN). The proposed model is designed to capture both the spatial features of satellite imagery and the temporal dynamics of climate data, offering enhanced predictive capabilities for key climate variables such as sea ice extent, glacier movement, and temperature variations. The dataset was split into 80% training and 20% testing with tenfold cross-validation, and the model was trained using the Adam optimizer. The results show that the proposed model achieved a remarkable accuracy of 97.43%, outperforming traditional CNN and RNN models. The model also demonstrated a precision of 98.12% for sea ice extent prediction, a 96.45% precision for glacier movement detection, and a mean squared error (MSE) of 0.35 °C for temperature predictions. These findings suggest that deep learning models, specifically the integration of transformer and 3D-CNN architectures, can significantly contribute to polar region climate monitoring, offering improved tools for scientific research and policymaking. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024. corrected publication 2024.

关键词： 3D convolutional neural network Attention-based transformer Climate dynamics Deep learning Glacier movement Polar region Remote sensing Sea ice extent Spatial–temporal analysis Temperature prediction

来源：评论

学校读者我要写书评

暂无评论

Crop and Fertilizer Recommendation System Applying Machine Learning Classifiers 1

Crop and Fertilizer Recommendation System Applying Machine L...

引用

1st IEEE International Conference on Emerging research in Computational science, ICERCS 2023

作者： Iniyan, S. Raja, M. Senthil Srinivasan, R. Santhanakrishnan, C. Srinivasan, Aravindan Srm Institute of Science and Technology School of Computing Department of Computing Technologies Tamilnadu Kattankulathur India Lakshmaiah Education Foundation Department of Computer Science and Engineering Andrapradesh Vaddeswaram India

ISBN: (纸本)9798350359756

In today's agriculture, increasing crop yields while minimizing resource use is critical for sustainable and profitable agriculture. The program addresses the urgent need for personalized crop and fertilizer recommendations in various agricultural regions of India. Using machine learning techniques such as linear regression, random forests, k-nearest neighbors and outlier detection, our model aims to provide farmers with clear guidance based on various environmental factors and soil. Linear regression algorithm is used to establish the relationship between input and product yield, K-Neighbors adds recommendations by identifying the similarity between farm features and neighboring farm features. This holistic approach is designed to increase the credibility of our proposal, given the unique challenges posed by India's diversity and climate. The model accepts soil characteristics, climate, crop history and fertilizer use patterns. We worked to create a variety of useful and flexible products that can be more efficient and practical and provide good results to farmers in different regions. The need of the project is an easy-to-use website that provides farmers with information about crop selection and planting. By leveraging the power of machine learning, the program helps modern agriculture, promotes sustainable practices and increases the overall profitability of Indian agriculture. © 2023 IEEE.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

5G Wireless Communication and IoT: Vision, Applications, and Challenges 2

5G Wireless Communication and IoT: Vision, Applications, and...

引用

2nd DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry, IDICAIEI 2024

作者： Bhivgade, Anushka Puri, Chetan Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Computer Science and Engineering Maharashtra Wardha442001 India

ISBN: (纸本)9798331528713

This article looks at the opportunities, application and challenges of 5G Wireless Communication Technologies and Internet of Things (IoT). A brief history from 1G to 5G is presented and the limitations of 4G and the introduction of 5G as a solution for problems with latency and speed. The paper also describes the 5G IoT concept, the architecture and advanced technologies with focus on different IoT applications such as smart agriculture and smart city. When speaking of aspects such as energy consumption, privacy and security concerns, as well as trade-offs strategies, it underlines how important collaboration is to achieve the benefits that the 5G IoT will bring. The paper itself provides a roadmap for next studies with a purpose of advancing development of the integrated, safe, and efficient wireless. As 5G Wireless Communication and IoT progresses the expectation is that it will enhance and revolutionalize several domains that will offer a scalable connectivity that is faster and more reliable. This join venture is believed to open new value adding opportunities for application in smart city, automobile, medical, industrial, robotic and so on several other fields. The term 5G IoT has also been used with the intention of establishing connections of several devices, very low latency and high degree of data rate for real time analysis and decision making. © 2024 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Quality of Service based Selfish Node Detection in Mobile Ad-Hoc Network 3

Quality of Service based Selfish Node Detection in Mobile Ad...

引用

3rd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2023

作者： Kannan, B. Maruthu Vadivel, G. Viswanathan, C. Reddy, P. Kiran Kumar Sphoorthy Engineering College Department of Computer Science and Engineering Telangana Hyderabad India University of Technology and Applied Science Department of Information Technology Salalah Oman Alpha College of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Malla Reddy Institute of Engineering and Technology Department of Computer Science and Engineering Telangana Secunderabad India

ISBN: (纸本)9781665462167

Mobile ad hoc networks (MANETs) are wireless networks containing a collection of wireless nodes interrelated with multi-hop communication paths. Mobile nodes can freely create and dynamically self-organize random and temporary wireless networks without pre-existing infrastructure. Hence, the transmission connection between two nodes breaks repeatedly due to node mobility. This causes an additional delay in the network's performance. All mobile nodes work together entirely regarding the distribution of their memory space. In actuality, though, several nodes may inconsiderately choose to cooperate partially;otherwise, not at all with other nodes. These selfish nodes minimize the whole data's accessibility. To solve these issues, quality-of-service-based self-node detection (QSND) in MANET is proposed. In this approach, the Quality of Service (QoS) parameters verifies the operation of a node. This approach uses the QoS parameters like packet loss ratio, packet delay ratio, and remaining energy ratio as the most significant components to evaluate the selfish nodes in the MANET. This approach minimized the delay and improved the network throughput. © 2023 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Robust Deep Transfer Learning Based Object Detection and Tracking Approach

引用

Intelligent Automation & Soft computing 2023年第3期35卷 3613-3626页

作者： C.Narmadha T.Kavitha R.Poonguzhali V.Hamsadhwani Ranjan walia Monia B.Jegajothi Electronics and Communication Engineering Periyar Maniammai Institute of Science&Technology(PMIST)Thanjavur613403India Department of Computer Science and Engineering Periyar Maniammai Institute of Science&TechnologyThanjavur613403India Department of Electrical and Electronics Engineering Periyar Maniammai Institute of Science and TechnologyThanjavur613403India Electrical Engineering Department Model Institute of Engineering&Technology(Autonomous)Jammu181122India Department of Computer Science and Engineering Shri Mata Vaishno Devi UniversityKatra182320India Center for Energy Research Chennai Institute of TechnologyChennai600069India

At present days,object detection and tracking concepts have gained more importance among researchers and business ***,deep learning(DL)approaches have been used for object tracking as it increases the perfor-mance and speed of the tracking *** paper presents a novel robust DL based object detection and tracking algorithm using Automated Image Anno-tation with ResNet based Faster regional convolutional neural network(R-CNN)named(AIA-FRCNN)*** AIA-RFRCNN method performs image anno-tation using a Discriminative Correlation Filter(DCF)with Channel and Spatial Reliability tracker(CSR)called DCF-CSRT *** AIA-RFRCNN model makes use of Faster RCNN as an object detector and tracker,which involves region proposal network(RPN)and Fast *** RPN is a full convolution network that concurrently predicts the bounding box and score of different *** RPN is a trained model used for the generation of the high-quality region proposals,which are utilized by Fast R-CNN for detection ***,Residual Network(ResNet 101)model is used as a shared convolutional neural network(CNN)for the generation of feature *** performance of the ResNet 101 model is further improved by the use of Adam optimizer,which tunes the hyperparameters namely learning rate,batch size,momentum,and weight ***,softmax layer is applied to classify the *** performance of the AIA-RFRCNN method has been assessed using a benchmark dataset and a detailed comparative analysis of the results takes *** outcome of the experiments indicated the superior characteristics of the AIA-RFRCNN model under diverse aspects.

关键词： Object detection tracking deep learning deep transfer learning image annotation

来源：评论

学校读者我要写书评

暂无评论

OblivTime: Oblivious and Efficient Interval Skyline Query Processing Over Encrypted Time-Series Data

引用

IEEE Transactions on Services computing 2025年第3期18卷 1602-1617页

作者： Ouyang, Huajie Zheng, Yifeng Wang, Songlei Hua, Zhongyun Harbin Institute of Technology School of Computer Science and Technology Guangdong Shenzhen518055 China The Hong Kong Polytechnic University Department of Electrical and Electronic Engineering Hong Kong Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen518055 China

Time-series data is prevalent in many applications like smart homes, smart grids, and healthcare. And it is now increasingly common to store and query time-series data in the cloud. Despite the benefits, data privacy concerns in such outsourced services are pressing, making it imperative to embed privacy assurance mechanisms from the outset. Most existing related works have been focused on querying for different types of aggregate statistics. In this paper, we instead focus on the secure support for advanced interval skyline queries, which allow to identify time series that are not dominated by any other time series within a query time interval. This is valuable for time-series data analytics in applications like remote health monitoring (e.g., identifying patients with high heart rates in a certain week). We present OblivTime, a new system framework for oblivious and efficient interval skyline query processing over encrypted time-series data. OblivTime is built from a synergy of time-series data analytics, lightweight cryptography, and GPU parallel computing, achieving stronger security guarantees and lower online query latency over the state-of-the-art prior work. Extensive experiments demonstrate that OblivTime can achieve up to 666\times speedup in online query latency over the state-of-the-art prior work. © 2008-2012 IEEE.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Enhancing Personality Classification through Textual Analysis: A Deep Learning Approach Utilizing MBTI and Social Media Data

Enhancing Personality Classification through Textual Analysi...

引用

2023 IEEE International Conference on Network, Multimedia and Information Technology, NMITCON 2023

作者： Mohan, G Bharathi Kumar, R Prasanna Elakkiya, R. Gorantla, Snehitha Amrita School of Computing Department of Computer Science and Engineering - Artificial Intelligence Amrita Vishwa Vidyapeetham Chennai601103 India Birla Institute of Technology and Science Department of Computer Science and Engineering Dubai345055 United Arab Emirates

ISBN: (纸本)9798350300826

Personality computing has grown significantly in use, with useful applications emerging in fields of study like human-robot interaction and recommendation systems. Traditional recommendation systems frequently run into issues with free riders, data scarcity, and a lack of understanding of user preferences. By strengthening the grasp of user preferences and increasing the precision of recommendations, the addition of well-established user personality features aids in resolving these problems. Therefore, the goal of this research is to take advantage of personality computing's numerous advantages while overcoming the drawbacks of current recommendation systems. This model achieved an accuracy of 97% on the test data because it was trained on pre-processed and padded sequences. By utilising LSTM layers, the model is better able to understand contextual information included in the text input and efficiently capture sequential dependencies. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Advancements in Crown Sheath Rot Detection using DenseNet121 and UNet in Rice Plant Leaf Analysis

Advancements in Crown Sheath Rot Detection using DenseNet121...

引用

2023 International Conference on Data science, Agents and Artificial Intelligence, ICDSAAI 2023

作者： Thilagavathy, R. Kumar, S.Senthil Deebalakshmi, R. Deepa, D. Kavitha, R. Kumar, L. Sathish Srm Institute of Science and Technology School of Computing Department of Computing Technologies Kattankulathur India School of Arts and Science Tamil Nadu Chennai India Srm Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu Tiruchirappalli India Kongu Engineering College Department of Computer Science and Engineering Tamil Nadu Perundurai India Karpagam Academy of Higher Education Department of Computer Applications TN Coimbatore India Vit Bhopal University School of Computing Science and Engineering MP Kotrikalan India

ISBN: (纸本)9798350348910

This article aims to investigate the leaf spot disease in rice, a condition that has been observed to cause substantial reductions in crop yield, ranging from 10% to 50%. The disease is characterized by the appearance of circular lesions on the leaves of rice plants, which gradually expand and cover the entire leaf surface, leading to the eventual death of the affected leaves. In order to achieve automation in the detection and severity classification of the disease under investigation, a range of deep learning models were utilized. These models encompassed Faster DenseNet121 and UNet. These methods proposed in this study was trained and tested using a dataset consisting of 1120 images. The findings of the study indicate that the DenseNet121 approach that yielded the highest level of success demonstrated a noteworthy classification accuracy rate of 95.23%. The results obtained from the integration of image processing techniques with deep learning models demonstrated superior performance compared to the analysis solely based on deep learning models. The integration described in this study presents a novel approach to enhance the efficiency of diagnosing leaf spot disease on rice. By leveraging advanced technology, this integration aims to reduce the time required for diagnosis, minimize the occurrence of human errors, and facilitate the timely application of suitable pesticides to mitigate the detrimental effects of the disease. © 2023 IEEE.

关键词： Integration

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：