检索结果-内蒙古大学图书馆

Mapping of Land Use and Land Cover(LULC)Using EuroSAT and Transfer Learning

Revue Internationale de Géomatique 2024年第1期33卷 1-13页

作者： Suman Kunwar Jannatul Ferdush Faculty of Computer Science Selinus University of Sciences and LiteratureRagusaItaly Deparment of Computer Science and Engineering Jashore University of Science and TechnologyJashoreBangladesh

As the global population continues to expand,the demand for natural resources ***,human activities account for 23%of greenhouse gas *** a positive note,remote sensing technologies have emerged as a valuable tool in managing our *** technologies allow us to monitor land use,plan urban areas,and drive advancements in areas such as agriculture,climate changemitigation,disaster recovery,and *** advances in Artificial Intelligence(AI),computer vision,and earth observation data have enabled unprecedented accuracy in land use *** using transfer learning and fine-tuning with red-green-blue(RGB)bands,we achieved an impressive 99.19%accuracy in land use *** findings can be used to inform conservation and urban planning policies.

关键词： Land use land cover EuroSAT transfer learning convolutional neural networks vision transformers

来源：评论

学校读者我要写书评

暂无评论

The Novel Protocol Uses Low Computational Complexity to Authenticate Edge Devices on Smart Grid Systems 9

The Novel Protocol Uses Low Computational Complexity to Auth...

引用

9th IEEE India International Conference on Power Electronics, IICPE 2023

作者： Kuppuswamy, Prakash Al Khalidi, Sayed Q.Y. Kumar, Purushottam Meeran, Ahmed Ali Shaik Sonia Varshini, Vijaya Computer Science Engineering SRM University Haryana Delhi-NCR India King Khalid University Department of Information Technology Abha Saudi Arabia Jazan University Department of Information Technology Jazan Saudi Arabia Bharathiyar University Computer Science Deparment Tamil Nadu Coimbatore India

ISBN: (纸本)9798350307252

Grid computing has emerged as a powerful paradigm for harnessing distributed computing resources to solve complex problems. In grid computing, various devices across different administrative domains collaborate to provide computational power and storage capacity. Sensor agent devices have become the backbone of modern technological systems such as Internet of Things (IoT), smart homes, industrial automation, and autonomous vehicles. These devices collect and process real-time data from the surrounding environment, providing crucial insights for decision-making, monitoring, and control purposes. However, the performance of these devices depends on space complexity and time complexity. Achieving optimum performance in sensor agent devices requires a delicate balance between space complexity and time complexity. Reducing one complexity may increase the other, and vice versa. Light weight authentication device-based algorithms play a vital role in verifying the identity of devices and ensuring secure communication within the grid and that needs to satisfy complexity. These protocols verify the identity of devices and users, ensuring that only authorized entities can access and interact with the data. In this article, we will explore a new light weight authentication protocol based on a block cipher i.e ELBC (Extended Linear Block cipher algorithm). The new authentication protocols are easy to implement and deploy in any kind of environment. The algorithm divides the authentication message into blocks and encrypts them using matrix multiplication. By generating an invertible key matrix and applying encryption and decryption equations, the proposed algorithm ensures secure communication. © 2023 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Numerical Modeling of Dissipative Cavity Quantum Electrodynamics without Markovian Approximation

Numerical Modeling of Dissipative Cavity Quantum Electrodyna...

引用

2024 International Symposium on Antennas and Propagation, ISAP 2024

作者： Na, Dong-Yeop Chew, Weng Cho Deparment of Electrical Engineering Pohang University of Science and Technology Pohang Korea Republic of Elmore Family School of Electrical and Computer Engineering Purdue University West Lafayette United States

ISBN: (纸本)9798350364774

We develop a numerical framework to analyze the dynamics of a dissipative cavity quantum electrodynamics without the Markovian approximation. For the correct quantization of electromagnetic fields in the presence of lossy dielectric objects in the free space, we employ the so-called BAMA formulation [1] which takes into account fluctuations to both radiation and medium losses. With the coarse-graining strategy, the BAMA fields (or modes) can be evaluated by using conventional computational electromagnetics numerical modes, e.g., FEM, FDTD, or MoM. We then incorporate the BAMA modes into the multimode Jaynes-Cummings model and solve the time-dependent Schrödinger equation to find probability amplitudes. © 2024 IEEE.

关键词： Schrodinger equation

来源：评论

学校读者我要写书评

暂无评论

Exploring the Feasibility of Transformer Based Models on Question Relatedness 24

Exploring the Feasibility of Transformer Based Models on Que...

引用

24th IEEE International Conference on High Performance Computing and Communications, 8th IEEE International Conference on Data science and Systems, 20th IEEE International Conference on Smart City and 8th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Application, HPCC/DSS/SmartCity/DependSys 2022

作者： Shu, Honglin Gao, Pei Yang, Ziwei Li, Chen Wu, Man Hong Kong Polytechnic University Department of Computing Hong Kong Nara Institute of Science and Technology Department of Information Science Nara Japan Kyushu Institute of Technology Department of Bioscience and Bioinformatics Iizuka Japan Keio University Deparment of Information and Computer Science Tokyo Japan

ISBN: (纸本)9798350319934

Professional question answering communities, such as Stack Overflow, are becoming a significant aspect of many intellectual endeavors. As a result, developing a strategy for swiftly locating relevant questions and answers can effectively assist experts in issue solving. Various detection models have been presented to address the problem of question-relatedness prediction, but all are sub-optimal since they cannot effectively capture the long-distance dependency of a long sequence. With the invention of the self-attention mechanism and transformer, a better approach to dealing with question-relatedness prediction has just emerged. The primary objective of this study is to investigate the feasibility of the transformer-based model for question-relatedness problems. We turn the question relatedness problem into a text classification problem and introduce a representative transformer-based model, namely Bidirectional Encoder Representation from Transformers (BERT), to deal with text classification. In our experiment, we show that BERT outperforms both SoftSVM and BiDotLSTM, implying that the transformer-based model has considerable potential to address the challenge in the question-relatedness problem. Furthermore, since we can re-formulate text classification problem into a link prediction problem, we discuss the possibility of incorporating the transformer-based approach and graph representation learning. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

CPW-fed Monopole Antenna with 3.5/5.5 GHz Band-Notched Characteristics for Ultrawideband Applications

CPW-fed Monopole Antenna with 3.5/5.5 GHz Band-Notched Chara...

引用

2024 International Symposium on Antennas and Propagation, ISAP 2024

作者： Tangthong, Nipont Moeikham, Pichet Sangpet, Patchadaporn Jamnien, Atthakorn Akkaraekthalin, Prayoot Chudpooti, Nonchanutt Deparment of Electronics and Telecommunication Engineering Faculty of Engineering Rajamangala University of Technology Thanyaburi Pathum Thani Thailand Deparment of Electrical Engineering Faculty of Engineering Rajamangala University of Technology Lanna Chiang Rai Chiang Rai Thailand KMUTNB Techno Park King Mongkut's University of Technology North Bangkok Bangkok Thailand Deparment of Electrical and Computer Engineering Faculty of Engineering King Mongkut's University of Technology North Bangkok Bangkok Thailand Deparment of Industrial Physics and Medical Instrumentation Faculty of Applied Science King Mongkut's University of Technology North Bangkok Bangkok Thailand

ISBN: (纸本)9798350364774

This research presents a printed ultrawideband monopole antenna designed with notches at the 3.5 GHz and 5.5 GHz frequency bands. The antenna incorporates a 50-Ω Coplanar Waveguide (CPW) feed, featuring a gradual central line and ground plane. To notch unwanted frequencies at 3.5 GHz and 5.5 GHz, an inverted triangle slot and an inverted U-shaped slot are integrated into the monopole patch. Operating across a frequency range of 2.62-12 GHz, the proposed antenna supports the UWB system while excluding the 3.22-3.62 GHz and 5.14-5.62 GHz bands. The lengths of the inverted triangle and U-shaped slots correspond to quarter and half wavelengths at 3.5 GHz and 5.5 GHz, respectively. The prototype has been fully developed and tested, showing its effectiveness in reducing Electromagnetic Interference (EMI) in WLAN/WiMAX bands. © 2024 IEEE.

关键词： Monopole antennas

来源：评论

学校读者我要写书评

暂无评论

Comparison of cloud and local HPC approach for MUSCLE-based multiscale simulations

Comparison of cloud and local HPC approach for MUSCLE-based ...

引用

7th IEEE International Conference on e-science Workshops, escienceW 201

作者： Rycerz, Katarzyna Nowak, Marcin Pierzchala, Pawel Ciepiela, Eryk Harezlak, Daniel Bubak, Marian AGH University of Science and Technology Deparment of Computer Science al. Mickiewicza 30 30-059 Krakow Poland University of Amsterdam Institute for Informatics Science Park 904 1098XH Amsterdam Netherlands AGH University of Science and Technology Academic Computer Centre - CYFRONET Nawojki 11 30-950 Kraków Poland

ISBN: (纸本)9780769545981

In this paper we present and compare a support for setting up and execution of multiscale applications in the two types of infrastructures: local HPC cluster and Amazon AWS cloud solutions. We focus on applications based on the MUSCLE framework, where distributed single scale modules running concurrently form one multiscale application. We also integrate presented solution with Grid Space virtual laboratory that enables users to develop and execute virtual experiments on the underlying computational and storage resources through its website based interface. Last but not least, we present a design of a user friendly visual tool supporting application distribution. © 2011 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Progression of Disease Forecasting in Recurrence Cervical Cancer Using Logistic Regression 7

Progression of Disease Forecasting in Recurrence Cervical Ca...

引用

7th International Conference on Electronics, Communication and Aerospace technology, ICECA 2023

作者： Geeitha, S. Renuka, P. Ramya, S. Sinduja, K. M.Kumarasamy College of Engineering Department of Information Technology Karur India Paavai Engineering College Deparment of Computer Science and Engineering Namakkal India Sri Krishna College of Engineering and Technology Department of Information Technology Coimbatore India

ISBN: (纸本)9798350340600

Cervical cancer is the fourth most prevalent disease in women globally as well as main cause of cancer- related mortality among women. The overall survival rates of cervical carcinoma patients are significantly impacted by the detection of recurrence. The disease is entirely treatable, though, if it is found in its early, precancerous levels. According to current figures, the death percentage a few decades ago was excessive. Women who have previously had treatment with CIN3 are most at riskof developing cervical cancer once more. The dataset includes information on the effects of various treatments on post- recurrence survival. The progression of a disease is detected in this research. Of the 4913 patients who were diagnosed withcervical cancer overall, 260 women with the disease suffered recurrences. The Data has been roughly categorized into 27 characteristics that are important for illness staging and therapy. Thevery important attributes selected are FIGO 2009, chemotherapy,radiotherapy, recurrence confirmed by a pathologist, etc. Five different models are trained to predict the progression. Logistic regression is finally predicted with a high level of accuracy of 96.3%. Two hundred and sixty patients with 27 attributes consistof a number of missing values. Research is implemented through the Orange platform. The missing values are balanced through Average and Most frequent data imputation method. Important attributes are selected through the ReliefF technique, and then disease progression is predicted by 5 different algorithms Logistic regression, Support vector machine, Naive Bayes, Stochastic gradient decent and neural network. Finally logistic regression predict the progression of a disease with highest accuracy of 96.3%. © 2023 IEEE.

关键词： Radiotherapy

来源：评论

学校读者我要写书评

暂无评论

Event-based non-parametric clustering of team sport trajectories

Event-based non-parametric clustering of team sport trajecto...

引用

IEEE International Conference on Big Data

作者： Fengchao Peng Yudian Ji Qiong Luo Lionel M. Ni Deparment of Computer Science and Engineering Hong Kong University of Science and Technology University of Macau

Strategy design and analysis is important in team sports, such as basketball and soccer. In this paper, we take basketball as an example and study how to cluster movement trajectories in the games to identify the strategies. This problem is challenging in that the trajectories are diverse and that it is unknown how many or what strategies are employed in the games. As a result, traditional parametric clustering methods are not directly applicable to the raw trajectory data. Therefore, we propose to align trajectories around the basket and simplify them based on movement directions and game events, including dribbling, passing, and shooting. Furthermore, we propose a non-parametric density peak (NPDP) method to cluster these simplified event trajectories. Our experiments on an NBA game dataset of 50,000 offenses show that, without parameter tuning, NPDP clusters all trajectories into groups of high similarity and identifies distinguishing movement strategies.

关键词： Trajectory Games Clustering algorithms Tuning Clustering methods Face Tracking

来源：评论

学校读者我要写书评

暂无评论

SHREC'10 track: Feature detection and description

SHREC'10 track: Feature detection and description

引用

3rd Eurographics Workshop on 3D Object Retrieval, EG 3DOR 2009

作者： Bronstein, A.M. Bronstein, M.M. Bustos, B. Castellani, U. Crisani, M. Falcidieno, B. Guibas, L.J. Kokkinos, I. Murino, V. Ovsjanikov, M. Patané, G. Sipiran, I. Spagnuolo, M. Sun, J. Department of Computer Science Technion - Israel Institute of Technology Israel Department of Computer Science Stanford University United States Department of Computer Science University of Verona Italy ÉCole Centrale de Paris Deparment of Applied Mathematics France Department of Computer Science - University of Chile Chile Princeton University United States Institute for Computational and Mathematical Engineering Stanford University United States Italian Institute of Technology Genova Italy

ISBN: (纸本)9783905674224

Feature-based approaches have recently become very popular in computer vision and image analysis applications, and are becoming a promising direction in shape retrieval. The SHREC'10 feature detection and description benchmark simulates the feature detection and description stages of feature-based shape retrieval algorithms. The benchmark tests the performance of shape feature detectors and descriptors under a wide variety of transformations. The benchmark allows evaluating how algorithms cope with certain classes of transformations and strength of the transformations that can be dealt with. The present paper is a report of the 3D Shape Retrieval Contest 2010 (SHREC'10) feature detection and description benchmark results. ©The Eurographics Association 2010.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A link obfuscation service to detect webbots

A link obfuscation service to detect webbots

引用

2010 IEEE 7th International Conference on Services Computing, SCC 2010

作者： Brewer, Douglas Li, Kang Ramaswamy, Laksmish Pu, Calton Deparment of Computer Science University of Georgia 415 Boyd GSRC Athens GA 30602 United States Georgia Institute of Technology College of Computing Atlanta GA 30332 United States

ISBN: (纸本)9780769541266

Web bot fraud activity currently accounts for a large number of web accesses. Current resistance methods such as CAPTCHA are not applicable for bot detection at the granularity of each click. In this paper, we propose a service that counters web bots which mimic human clicks by walking random links. We base our defense on systematically applying link obfuscation. The obfuscation is designed as a service that can be applied to websites without changes from web developers and without changing the behavior of human users. The service for resisting web bots is called Decoy Link Design Adaptation (DLDA) and works by transparently modifying every page of a protected website. The modifications are made such that walking web bots cannot traverse valid paths through the website. Specifically, DLDA modifies each original link on the page surrounding it with a group of invalid links. These obsfucated links are carefully styled to be unnoticed or avoided by human users;however, they require significant effort for programs (bots) to identify. Experiments show that DLDA has a very high detection rate for web bots and near zero false positives. DLDA can detect 80% of walking bots ending a session after one minute of inactivity (no clicks). The detection rate increases to 100% when the session is ended where multiple visits of the bots can be grouped into a single session. © 2010 IEEE.

关键词： Websites

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：