检索结果-内蒙古大学图书馆

Multispectral Satellite Data Classification Using Rank Correlation Similarity Index and Automatic Labeling Technique

引用

SN computer science 2024年第8期5卷 1073页

作者： Ain, Arindom Gogoi, Minakshi Chutia, Dibyajyoti Dept. of Computer Science and Engineering GIMT Under Assam Science and Technology University Assam Guwahati India Dept. of Computer Science and Engineering Girijananda Chowdhury University Assam Guwahati India NESAC Umium Shillong India

Multispectral satellite image classification is crucial in remote sensing and image analysis, serving various applications like water area extraction, urban region classification, and vegetation monitoring. Model-based classification, particularly supervised learning approaches, heavily relies on manually annotated training samples, which are labor-intensive and subject to human bias. However, solely depending on features derived from individual pixels may fail to capture spatial contextual information effectively and manage mixed pixels and various types of noise, resulting in classification inaccuracies. To address these challenges, this research proposes a novel unsupervised learning approach and automatic labeling technique (ALT). This approach utilizes collective information from groups of pixels instead of relying solely on individual pixels for identification and extraction of meaningful unique patterns which serves as the most significant factor for satellite image classification. A new similarity index, the patch similarity index (PSI), is generated by incorporating the rank correlation similarity index (RCSI). The PSI is used to determine the similarity factor both between the patches and within the patch. Subsequently, a clustering algorithm is employed to group pixels into four distinct classes: vegetation, water, built-ups, and open land. Additionally, ALT streamlines the post-classification process by reducing the need for manual intervention in mapping clusters to the actual class label. The proposed method offers a more accurate and reliable unsupervised classification for multispectral satellite imagery, promising enhanced efficiency and reduced manual labor. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Automatic labeling technique Frequent masking Multispectral Patch similarity index Rank Correlation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Domain-Specific ASR Performance Using Finetuning and Zero-Shot Prompting: A Study in the Medical Domain 6

Enhancing Domain-Specific ASR Performance Using Finetuning a...

引用

6th Doctoral Symposium on Intelligence Enabled Research, DoSIER 2024

作者： Maulik, Utsav Bandyopadhyay Mitra, Pabitra Sarkar, Sudeshna Dept. of Computer Science and Engineering IIT Kharagpur West Bengal India

Domain Adaptation has emerged as an important development in Speech Recognition systems for improving the transcription accuracy of the input audio. This study explores the enhancement of Domain-specific Automatic Speech Recognition performance through finetuning and postprocessing using Large Language Models, focusing specifically on the medical domain. We investigate how domain-specific finetuning and advanced text postprocessing techniques can significantly improve transcription accuracy in medical contexts, reducing errors in specialized terminology, acronyms, and abbreviations. Our findings highlight the benefits of integrating Large Language Model based postprocessing with Automatic Speech Recognition systems to achieve better results in complex domains. © 2025 Copyright for this paper by its authors.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Smart Plant Watering System for Advanced Irrigation 2

Smart Plant Watering System for Advanced Irrigation

引用

2nd IEEE International Conference on Advances in Information Technology, ICAIT 2024

作者： Pujitha, Pasupuleti Sai Bhoomika, H.R. Saideep, Konduri Rahul Reddy, T. Banshal, Sumit Kumar Karmakar, Mousumi Shekhar, R. Dept. of Computer Science & Engineering Alliance University Bangalore India

ISBN: (纸本)9798350383867

The Smart Plant Watering System is an Internet of Things (IoT) solution for automated plant irrigation. It combines an ESP8266 Wi-Fi module for real-time monitoring with soil moisture and DHT11 sensors for data collection. It makes use of tools such as Blynk and Thing Speak to facilitate data visualization and remote control. An online crop recommendation systems using ML approaches and written in Python makes recommendations for the best crops to plant depending on the analysis of sensor data. With its ability to maximize irrigation, reduce water use, and improve crop management, this system represents a major breakthrough in precision agriculture for increased productivity and environmental sustainability. © 2024 IEEE.

关键词： Soil moisture

来源：评论

学校读者我要写书评

暂无评论

Enhancing Movie Recommendation Efficiency Using Ensemble Learning Techniques

Enhancing Movie Recommendation Efficiency Using Ensemble Lea...

引用

2024 International Conference on Emerging Innovations and Advanced Computing, INNOCOMP 2024

作者： Nitasha Pandey, Aniket Kumar Yadav, Ankit Mishra, Subrat Medhanshi Chandigarh University Dept. of Computer Science and Engineering Mohali India

ISBN: (纸本)9798350376470

This research paper explores the 'Movie Dataset' to create a better movie recommendation. The data includes many features such as genre, ratings, players, and user preferences. Our main goal is to find the best combination model combining SVD (Singular Value Decomposition), SVD++ (SVD with Implicit Feedback) and KNN Baseline (K Nearest Neighbors with Baseline) recommendation algorithms to improve prediction accuracy and recommendations. The rapid expansion of digital media platforms has created a lot of information in the entertainment industry, making movie recommendations very important for the development of consumers. Through our research, we focus on the development of personalized movie recommendations and user satisfaction in the field of digital entertainment. © 2024 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Dynamic Task Scheduling for Load Balancing in Cloud Environments to Enhance Resource Allocation and Performance Efficiency

Dynamic Task Scheduling for Load Balancing in Cloud Environm...

引用

2024 International Conference on Innovations and Challenges in Emerging Technologies, ICICET 2024

作者： Khan, Mohammad Imran Sharma, Kapil Amity University Dept. of Computer Science and Engineering Gwalior India

ISBN: (纸本)9798350319019

Effective resource distribution and speed efficiency are key to giving people the best service in cloud computer settings. Dynamic task ordering is a key part of reaching these goals because it uses available resources to easily distribute jobs while balancing the load. Within this paper, we suggest a new way to handle dynamic task scheduling that will help make cloud settings better at allocating resources and optimizing speed. The suggested approach uses a dynamic scheduling program that considers things like available resources, job needs, and present system load to make smart schedule choices. With dynamic task assignment, the system can change to changing job conditions in real time, making better use of resources and reducing response times. The suggested method includes load balance, which spreads jobs fairly among available resources so that computer or server doesn't get too busy. A fair job division keeps the system running smoothly, even during times of high usage. To make the best use of resources and reduce energy use, the suggested method also includes techniques like virtual machine consolidation and transfer. There is better resource usage and energy efficiency in the system because tasks are centralized on fewer actual computers and resources are allocated based on job demand. Based on results from experiments, the suggested method is better at allocating resources and improving performance compared to standard scheduling methods. In terms of shorter reaction times, higher output, and better use of resources, the results show big gains. © 2024 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Plant Disease Detection for Guava and Mango using YOLO and Faster R-CNN 2

Plant Disease Detection for Guava and Mango using YOLO and F...

引用

2nd IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2024

作者： Shetty, Kruthi U. Javed Kutty, Rida Donthi, Khushi Patil, Anuj Subramanyam, Natarajan Pes University Dept. of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350360523

Traditional methods of plant disease detection are cumbersome and prone to errors that cannot be avoided. Plant disease detection can help prevent crop losses and ensure food security. The system employs state-of-the-art deep learning techniques to automatically detect and classify plant disease in agricultural fields. The proposed system addresses the challenges associated with identifying plant diseases, which often have similar visual characteristics, by using a combination of deep learning and computer vision methods, specifically employing the YOLO (You Only Look Once) and Faster Region-Convolutional Neural Network with a ResNet-152 backbone. The system is trained on a custom dataset where the images were captured in an uncontrolled environment, specifically focusing on two plant leaves, namely Guava and Mango, to achieve high accuracy in identifying diseases in real-world field conditions. The proposed system has the potential to revolutionize plant disease detection and ensure food security. © 2024 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Advances in Remote Sensing Technologies for Ecological Monitoring and Applications in Carbon Stock Estimation 3

Advances in Remote Sensing Technologies for Ecological Monit...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Sadhasivam, Shankaripriya Gayathri, G. Poongothai, P. Pavithra, S. Dept. of Computer Science and Engineering Chennai Institute of technology Chennai India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527549

This review explores recent advancements that are made in remote sensing, enabling detailed analysis of our ecosystem through high resolution and multispectral imaging. The recent advancements in remote sensing includes developments useful for generation of synthetic images using GAN such as StyleGAN3 and for estimation of carbon stocks in forest using OBIA. Ecotones like mangroves and saltmarsh are crucial for carbon sequestration but mapping them accurately was challenging due to spectral similarity and seasonal variations. Focusing on coastal protection by this review examines the mapping methodologies such as random forest classification, OBIA and FID for habitat distinction, canopy area assessment and analysis. Through these technologies data accuracy can be enhanced for better monitoring. This review concludes with a discussion of AI-powered image synthesis and classification. © 2025 IEEE.

关键词： Carbon sequestration

来源：评论

学校读者我要写书评

暂无评论

Integrating Deep Learning Techniques for Enhanced Cyclone Prediction and its Impact on Air Quality Index Utilizing Satellite Imagery

Integrating Deep Learning Techniques for Enhanced Cyclone Pr...

引用

2024 IEEE Students Conference on engineering and Systems, SCES 2024

作者： Vijayakumar, Sushruth Jamadhiar, Sonakshi Raj, Srujan M Mr, Vishnudeep Saritha, K. PES University Dept. of Computer Science Engineering Bengaluru India

ISBN: (纸本)9798350374711

Tropical cyclones (TCs greatly impact ecosystems and weather patterns, often leading to catastrophic outcomes this research explores dynamic relationship between the Air Quality Index (AQI) and Tropical Cyclones (TCs), examining changes in air quality during different stages of TCs. Focusing on Cyclone Biparjoy's impact on India's coastline in June 2023, we uncover its influence on air quality. The study shows good predictive performance by utilizing meteorological data, satellite observations, and machine learning algorithms such as CNN and ConvLSTM. Results show promising outcomes, with CNN achieving an RMSE of about 12.03 and an MAE of approximately 8.523 for TC intensity prediction, and ConvLSTM producing an RMSE of approximately 0.22 and a loss of around 0.04 for TC track prediction. Additionally, regression techniques using meteorological data from Tuetempo for AQI prediction were employed. The ExtraTrees Regression model exhibited strong predictive performance with an RMSE of approximately 19.627, while the Xgboost model had a slightly higher RMSE of around 21.72 our dataset included meteorological data from Tuetempo website for AQI forecasts and datasets like Hursat and INSAT 3D satellite photos for TC-related data, this work offers important insights into the dynamics of air quality during TC events. © 2024 IEEE.

关键词： Tropical cyclone

来源：评论

学校读者我要写书评

暂无评论

Weather Forecasting Web application 4

Weather Forecasting Web application

引用

4th IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2024

作者： Gowrav, N. Dhanush, V. Chavan, Chandrashekhar Pomu Pes University Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798331518981

Weather Refers to the Atmosphere state of certain area and time in terms of temperature, clouds, winds, dry state, sun and rain. The most important geophysical phenomenon that affects us is weather. Weather fluctuates greatly and is impacted by a number of elements including cloudiness, climate, and other variables. The primary goal of the project is to develop an app that can deliver weather forecasts for each city on the planet. We wish to use the ReactJS java script technology to create a web application. © 2024 IEEE.

关键词： Java programming language

来源：评论

学校读者我要写书评

暂无评论

A Framework to Find Single Language Version Using Pattern Analysis in Mixed Script Queries 2

A Framework to Find Single Language Version Using Pattern An...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Chaudhary, Anu Shekhar, Shashi Gla University Dept. of Computer Science and Engineering Mathura India

ISBN: (纸本)9798350371055

Pattern analysis for converting a complete mixed code into a single language after determining confidence levels is a systematic approach crucial for applications requiring language uniformity. The process begins by tokenizing the mixed code into individual words or segments and employing a language identification algorithm to assign potential languages with associated confidence scores to each segment. Establishment of a confidence threshold allows for the reliable selection of dominant languages within the mixed code. Segmentation based on confidence levels and the application of a majority language rule ensures the prioritization of the most reliable language segments. In cases where confidence falls below the threshold or ambiguity arises, a fallback mechanism can be implemented, offering options like defaulting to a predefined language or flagging for manual review. The conversion strategy is then formulated based on the identified dominant language, utilizing tools such as machine translation services or language-specific processing libraries. The final output is a unified, single-language version of the mixed code, providing consistency and reliability in diverse linguistic contexts. The bulk of the words are Hindi, it has been noted after handing to the model. This is the reason these mixed codes need to be translated into majority language script. Make a table of replacements to swap out the unclear acronym with the matching term. There are 79 words in all, and 1 of those words are erroneous;thus, the correctness of the work is (78 / 79) × 100=98.73 %, and the mistake rate is (1/79)× 100=1.27%. © 2024 IEEE.

关键词： Dominant language Pattern analysis Segmentation Single language version

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：