检索结果-内蒙古大学图书馆

Multi-Agent Systems for Collaborative Intelligence (ICMSCI), International Conference on

作者： I. Vasudevan P. Malathi S. Siddik P.R Therasa M.Mohamed Nasurudeen R.M.Dilip Charaan Dept.of CSE Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India Dept of Computer Science Saveetha College of Liberal Arts and Sciences SIMATS Dept.of EEE Pavaai Engineering College Namakkal India Dept.of CSE R.M.K Engineering College Kavaraipettai India Dept.of CSE V.S.B Engineering College Karur India

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

Cyber security is one the most challenging task in today's world. Most of the existing Li-Fi technology in wireless sensor network is to detect the data within the short range of distance less accuracy. In this research, we proposed a Smart based Secure Morse Code (SSMC) technique. Here there are two part, first is encoding and next is decoding. This proposed encoding technique takes user input in text based form and convert these text to standard morse code pattern and decoding does in the opposite direction. The transmitter parts encode the user input and send the pattern through laser module. The receiver part receives the pattern sends to microcontroller and then decodes and displays the data. In our experiment results shows that the proposed technique can transmit data over long distance with help of morse code encoding decoding algorithm. This technique takes 5ms for the whole transmission and process the transmission accurately.

关键词： Wireless communication Wireless sensor networks Codes Transmitters Receivers Light fidelity Encoding Decoding computer crime Standards

来源：评论

学校读者我要写书评

暂无评论

Augmented Reality based WayFinder System in Libraries

Augmented Reality based WayFinder System in Libraries

引用

Automation, Computing and Renewable Systems (ICACRS), International Conference on

作者： Aiswarya R Sreeram V K Anchana Jinesh K Sneha Vp Hema P Menon Dept.of Computer Science and Engineering Sreepathy Institute of Mnagement and Technology Vavanoor Palakkad Kerala India

Advancement in technology can be utilized to ease workloads in many scenarios. In libraries, the search for a particular book may take a lot of time, and memorizing the position of each book is not an easy task and may result in reducing a person’s interest in visiting the library. Usage of Augmented Reality, helps in visualizing the plots of the library. After combining with GPS, the system will be able to suggest the path to desired book in minimum required time. In libraries, there can be multiple paths to reach a particular book. The proposed system compares the multiple paths to find the best way with minimum distance to reach the desired book. The developed Augmented Reality wayfinding system revolutionizes the library experience by overlaying directional information or real environments through a smartphone camera. Scanning a provided QR code in the library helps the users to access the interface of the system and search for the required book. Innovation of such a system not only simplifies the search for books but also enables customers to check book availability and stock levels via a database. It also suggests alternatives, if the specific book is unavailable. By engaging such on-screen bots overall user experience can be enhanced and workload can be minimalized.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Application of HPC and big data in post-pandemic times

引用

Earthquake Research Advances 2021年第3期1卷 21-28页

作者： Henry M.Tufo David A.Yuen Gabriele Morra Matthew G.Knepley Bei Zhang Shi Chen Dept.of Computer Science University of ColoradoBoulderUSA Dept.of Applied Physics and Applied Mathematics Columbia UniversityUSA College of Information Science and Engineering and College of Marine Geosciences Ocean University of ChinaQingdaoChina Dept.of Physics and Earth Sciences University of LouisianaLafayetteLouisianaUSA Dept.of Computer Science and Engineering State University of New YorkBuffaloUSA Institute of Geophysics China Earthquake AdministrationBeijingChina Beijing Baijiatuan Earth Science National Observation and Research StationBeijingChina

We lay out the ramifications of the 2020 pandemic for all people in geosciences,especially the young,and argue for significant changes on training and career *** focus primarily on its devastating impact in USA and compare with that in other countries especially *** review the potential effect for the next four years or so on the aspirations of an academic career versus more realistic career *** urge people in mid-career about the need to reassess previous *** stress the need for students or researchers to acquire technical skills in high-performance computing(HPC),data analytics,artificial intelligence,and/or visualization along with a broad set of technical skills in applied computer science and *** give advice about hot prospects in several areas that have great potential for advancement in the coming decade,such as visualization,deep learning,quantum computing and information,and cloud computing,all of which lie within the aegis of *** forecast is that the pandemic will significantly reshape the job landscape and career paths for both young and established researchers and we discuss bluntly the dire situation facing junior people in geosciences in the aftermath of the pandemic around the world until 2024.

关键词： Geophysics High-performance computing Higher education Post-pandemic era

来源：评论

学校读者我要写书评

暂无评论

Optimizing Synergy in Deep Learning for Accurate Diabetic Retinopathy Identification and Staging

Optimizing Synergy in Deep Learning for Accurate Diabetic Re...

引用

Electronics and Sustainable Communication Systems (ICESC), 2020 International Conference on

作者： Raghunadha Reddi Dornala Adusumilli Ramana Lakshmi Sudhir Ponnapalli Ganji Ramanjaiah Kopparthi Poorna Sairamakrishna Department Of Computer Science & Engineering PVP Siddhartha Engineering College India Dept.of Computer Science & Engineering (Data Science) R V R & J C College of Engineering Guntur Andhra Pradesh India Sagi Rama Krishna Raju Engineering College Bhimavaram

ISBN: (数字)9798350379945

ISBN: (纸本)9798350379952

Millions of people with diabetes suffer from diabetic retinopathy (DR), the primary cause of vision loss in human beings. Early detection and precise staging are essential to manage and treat DR effectively. In recent years, deep learning (DL) approaches have demonstrated encouraging results in automating the staging and detection of DR from retinal images. Developers have designed many existing systems to detect and classify DR images based on their staging. The proposed approach, also called a novel method, increases the detection rate regarding affected regions. Various architectures such as Residual Networks (ResNets), Attention Mechanisms, and Convolutional Neural Networks (CNNs) improved the performance of the proposed approach by obtaining significant data from retinal images. Transfer learning mainly transfers the disease and standard patterns from the training to testing models. An additional advantage of the proposed approach is that it combines advanced preprocessing and feature extraction techniques. The preprocessing technique reduces the noise and filters the images without losing the pixel quality. The feature extraction helps extract the essential patterns from the input DR images that help detect the affected regions. Experimental analyses were applied using two publicly accessible datasets, such as the Kaggle DR dataset and Kaggle Fundus images, which contain various retinal pictures with different levels of DR severity. Comparing our results against state-of-the-art methods, we find considerable identification and stage accuracy increases.

关键词： Deep learning Diabetic retinopathy Accuracy Attention mechanisms Noise Transfer learning Feature extraction Retina Convolutional neural networks Diseases

来源：评论

学校读者我要写书评

暂无评论

Advancements in Flood Mapping Methodologies: A Comprehensive Review

Advancements in Flood Mapping Methodologies: A Comprehensive...

引用

IEEE Recent Advances in Intelligent Computational Systems (RAICS)

作者： Divya V Chandran J Anitha Amrutha Vijayakumar Anjana Raveendran Dept. of Electronics and Communication Engineering Adi Shankara Institute of Engineering and Technology Kalady India Dept.of Computer Science Engineering Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (数字)9798350381689

ISBN: (纸本)9798350381696

This review aims to comprehensively assess the recent advancements in flood mapping methodologies and technologies. By analyzing diverse techniques and approaches employed in flood mapping, this review seeks to present an in-depth overview of the current landscape of this field. The primary focus is on evaluating the strengths and limitations inherent in various flood mapping methods. Special attention will be given to exploring the integration of remote sensing technologies and geographic information systems (GIS) in flood mapping. Additionally, the review will delve into the transformative impact of machine learning and artificial intelligence on enhancing the precision and efficiency of flood mapping processes. Recent developments in flood mapping have significantly elevated the accuracy and reliability of the techniques employed. The integration of AI technologies with remote sensing methods has notably contributed to this advancement. Conventional approaches to flood mapping have traditionally relied on multiple methodologies to comprehend potential flood impacts. However, these methods often prove laborious, resource-intensive, and may lack access to real-time data, posing limitations for precise flood mapping and prediction. These identified limitations underscore the critical need for the development of more robust flood mapping techniques. Addressing these challenges is essential for enhancing flood risk assessment, improving management strategies, and ensuring better preparedness for future flood events.

关键词： Accuracy Reviews Heuristic algorithms Real-time systems Satellite images Floods Reliability

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Flood Detection System Using Semantic Segmentation

Deep Learning-Based Flood Detection System Using Semantic Se...

引用

International Conference on Circuit, Power and Computing Technologies (ICCPCT)

作者： Divya V Chandran J Anitha Anusree A R Gowri Nair Dept.of Computer Science Engineering Karunya Institute of Technology and Sciences Coimbatore India Dept. Electronics and Communication Engineering Adi Shankara Institute of Engineering and Technology Ernakulam India

ISBN: (数字)9798350372816

ISBN: (纸本)9798350372823

Floods cause immense damage worldwide, resulting in significant financial losses and loss of life. Existing flood detection methods often face limitations, including delays and errors due to manual data interpretation and limited coverage. In this study, we propose a novel flood detection system that leverages deep learning techniques for semantic segmentation. Our system employs a U-Net architecture to analyze aerial and satellite images, identifying flood-affected areas at a pixel level. Trained on a diverse dataset of labeled flood images from various regions, our model is both robust and adaptable. Notably, our system achieves an Intersection over Union (IoU) score of 0.85, surpassing traditional methods in accuracy. This advanced system offers the potential to provide real-time flood information, enhancing disaster response and management. With real-time flood mapping, emergency services can better understand the disaster’s scope and plan rescue operations more effectively. Improved emergency response and resource management become possible with timely, precise data on flooded areas, allowing for informed decisions regarding evacuation, relief distribution, and infrastructure maintenance. Future work will focus on integrating additional data sources, such as weather conditions and water flow rates, to further enhance system performance.

关键词： Accuracy Soft sensors Semantic segmentation Refining computer architecture Real-time systems Data models

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation and Task Scheduling in Cloud Computing Using Improved Bat and Modified Social Group Optimization 2

Resource Allocation and Task Scheduling in Cloud Computing U...

引用

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

作者： Ganesan, Thirusubramanian Almusawi, Muntather Sudhakar, K. Sathishkumar, B.R. Kumar, Komuravelly Sudheer Cognizant Technology Solutions TX United States The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Dept.of Ai & Ds Bengaluru India Sri Ramakrishna Engineering College Department of Ece Coimbatore India Sr University School of Computer Science & Artificial Intelligence Warangal India

ISBN: (纸本)9798350372892

Nowadays, Cloud computing is growing quickly with a maximum number of users and clients that are reaching from single users to huge business organizations. The cloud is facing significant challenges in managing large volumes of data and several cloud resources due to its rapid growth. Several optimization algorithms faced a challenge in scalability when working with more complicated scheduling scenarios. A combination of Resource Allocation and Task Scheduling using Improved Bat Optimization Algorithm (IBOA) by using dynamic weights with the speed update formula and increasing the random searchability and Modified Social Group Optimization (MSGO) by modifying the acquiring phase is introduced in this research. The developed IB and MSGO methods are simulated using a various simulation setup and the obtained results like response time, utilization of resources and energy consumption are compared against existing methods to measure the efficiency. For 100 tasks, the proposed IB and MSGO method achieved 32.5 watts of energy. The obtained results exposed that IB and MSGO method has better performance compared with the existing method namely Multi-Objective Task Scheduling Grey Wolf Optimization (MOTSGWO) in terms of energy consumption. © 2024 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Identification of Kidney Related Disease Using Deep Learning

Identification of Kidney Related Disease Using Deep Learning

引用

作者： S.Selvaraj Thangarajan R Ramya R Nandhini N Department of Computer Science and Design Kongu Engineering College Dept.of Information Technology Kongu Engineering College Dept.of Computer Science and Engineering Kongu Engineering College Department of Computer Science and Engineering Kongu Engineering College

Nowadays,kidney stone problems are frequent,as more people are suffering from acute discomfort caused by kidney *** main cause of this disease is a high level of unhealthy food consumption and a low level of water *** health problems can be avoided if we drink enough water,but in this fast-paced world,people often forget to do *** a result,stone concerns have arisen and been discovered as stone sizes have grown *** employ coronal computed tomography(CT) scan results and other study data on the belly and thorax to determine the sizes of stones and detect them in *** could assist in locating the *** currently utilize a back propagation method to assist them spot problems with an accuracy of 85 *** suggested deep learning methods and approaches,which process training data and data sets with labels,to find a more accurate level than the previous *** obtain an accurate result rate,a larger number of photos are compared and analyzed with the scanned *** accuracy level has been raised to 97.6%.So that we can acquire reliable results and diagnose problems *** can observe how deep learning works and how it handles urological difficulties in this paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Convenient Machine Learning Model for Cyber Security 5

A Convenient Machine Learning Model for Cyber Security

引用

5th International Conference on Computing Methodologies and Communication, ICCMC 2021

作者： Thanuja, N. N R, Deepak Bangalore Inistitute of Technology Vtu Dept of Computer Science and Engineering Bangalore Karnataka India Hkbk College of Engineering Vtu Dept.of Computer Science and Engineering Bangalore Karnataka India

ISBN: (纸本)9781665403603

In recent years, deep neural network approaches have been generally embraced for AI undertakings, including characterization. Nonetheless, they were demonstrated to be helpless against antagonistic assaults. This research work proposes a GAN based model, another system that utilizes the expressive ability of generative models to protect profound neural organizations against such assaults. Security assaults are getting progressively predominant as digital aggressors abuse framework vulnerabilities for monetary benefit. The digital interruptions imperil our gadgets constantly, they have numerous extreme results, for example, the unapproved divulgement of data, the altering, decimation, and expungement of information. Consequently, unsupervised and viable identification is required to react to these malevolent interruptions against systems and PCs. Many investigations have been finished with both measurable learning strategies and neural networks. Present day arranged frameworks are getting enormous measured and dynamic. Therefore, existing security models experience the ill effects of adaptability issue, where it gets infeasible to utilize them for present day arranged frameworks that contain hundreds and thousands of hosts and vulnerabilities. The objective of this examination is to build up a repeatable procedure to distinguish digital assaults that is quick, exact, and adaptable. The procedure ought to assess various information sources so as to increase a far-reaching image of client action over different frameworks. Client action designs experience typical changes for the duration of the day, and frequently those examples contrast from designs that happen on ends of the week. The model is required to separate between typical changes and anomalous client exercises. A profound learning calculation is utilized to prepare a neural system to distinguish suspicious client exercises. © 2021 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Occluded Retail Products Detection Through Attention-Reweighted

Occluded Retail Products Detection Through Attention-Reweigh...

引用

2022 IET International Conference on engineering Technologies and Applications, IET-ICETA 2022

作者： Chan, Hung-Tse Chen, Vincent Hsia, Chih-Hsien National Taiwan University of Science and Technology Dept. of Electronic and Computer Engineering Taipei Taiwan Interlake High School WA United States National Ilan University Dept.of Computer Science and Information Engineering Yilan Taiwan Chaoyang University of Technology Dept. of Business Administration Taichung Taiwan

ISBN: (数字)9781665491389

ISBN: (纸本)9781665491389

In recent years, developments in artificial intelligence (AI) and computer vision (CV) have led to an increase in research regarding retail product detection. However, effective CV use for identifying objects continues to face major obstacles, such as customers% random placement of products at checkout partially obscuring items from view. This paper explores the use of faster region-based convolutional neural networks (Faster RCNN) and attentional reweighting to detect obscured retail products. This attention-based method allows CV to identify and process various occlusion patterns. While the training set used to teach the network excluded heavily occluded data, the test set included a range of obscuration levels to accurately reflect the random positioning of products in real life. Experimental results suggest that the proposed method returns better detection accuracy with occlusion problems than current approaches employing convolutional neural networks (CNNs). © 2022 IEEE.

关键词： Convolutional neural networks

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：