检索结果-内蒙古大学图书馆

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...

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

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

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

A review on 3D image reconstruction on specific and generic objects

引用

Materials Today: Proceedings 2023年 80卷 2400-2405页

作者： Shalma, H. Selvaraj, P. Dept. of Computer Science and Engineering SRM Institute of Science and Technology Kattankulathur Chennai India Dept. of Information Technology SRM Institute of Science and Technology Kattankulathur Chennai India

With the emergence of various techniques involved in deep learning the researchers of computer vision tends to focus on the strategies such as object recognition and segmentation of image. This has inclined to accomplish the deep learning techniques in 3D reconstruction of both specific and generic objects. As the space for reconstruction of 3D images either in single or multi view has envisioned the researchers to concentrate on the available technologies used for reconstruction. With the available built in methods and technologies in deep learning, the performance of the proposed methods were reviewed and analyzed using several parameters. As the remaking of 2D images is still in the beginning stage, it is important to study the 3D shape representations, various network architecture, methodologies and approaches behind 3D reconstruction. In this work a review of deep learning methods for single or multiple RGB images of specific and generic object 3D reconstruction was done. Several methods and their importance were also discussed along with the challenges encountered and with further research directions. This paper critically analyzes the various 3D Shaped Representations, 3D Data Network Architectures, dept. Estimation methods, Multi View Representations and the Data Representation Techniques. © 2021

关键词： Object recognition

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

Design and Development of Expense App

Design and Development of Expense App

引用

2024 International Conference on Advances in Computing Research on science engineering and Technology, ACROSET 2024

作者： Girdhar, Gunit Kumar, Sachin Bhardwaj, Anuj Sharma, Megha Chandigarh University Dept. of Computer Science & Engineering Mohali India

ISBN: (纸本)9798350388800

With the help of Expense Tracker, you can easily and intuitively manage your revenue and costs while keeping track of your everyday, weekly, monthly, and annual spending. Users may choose the kind of expenditure, add location, upload more data, choose the amount of expense, and more. Additionally, the relational database will save this data. Users have the option to see and sort spending weekly, monthly, or annually. We may track the spending and minimize the amount of human computations for their costs by employing this. This allows a user to enter their income to get an estimate of their daily costs, and the results are saved for each individual user. Individuals who frequently go on excursions or to the theatre with friends might use this tracker to keep tabs on their spending. They will find it simple to split the bill using this tracker. This will show graphs according to the chosen perspective. Additionally, a user may write in this TR his monthly income or monthly expenditure cap. An integrated feature set is offered by this tracker system to assist you in managing your spending and cash flow. © 2024 IEEE.

关键词： Cost benefit analysis

来源：评论

学校读者我要写书评

暂无评论

Machine Learning - Driven Approaches for Detection and Analysis of Phishing attacks: A Robust Framework for Cybersecurity 7

Machine Learning - Driven Approaches for Detection and Analy...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Sarvan, N.D.S.S. Sai Ram Reddy, Venkata Jain, Darshan Rakesh, Guntupalli Anguraj, Dinesh Kumar Kl University Dept. of Computer Science Engineering Guntur India

ISBN: (纸本)9798350359299

Phishing is the attempt to trick someone into disclosing confidential and private information by using internet communication, such as bank account details, passwords, credit/debit card details, and usernames. The accuracy of foreseeing such phishing assaults can be substantially enhanced through utilizing these algorithms. The primary objective of this research work is to enhance internet security by providing a dependable and productive method for detecting phishing websites. To achieve this, a machine learning-based approach was employed, utilizing various models trained on a dataset of phishing website attributes. The study evaluated a range of machine learning algorithms and classifiers, including Naive Bayes, Support Vector Machine, K-Nearest Neighbors, Gradient Boosting, Decision Tree, Random Forest, Bagging, Voting, and AdaBoost Classifiers. These evaluation parameters are used to determine the efficiency of the machine learning models including F1 Score, Accuracy, Precision, and Recall values. By training the dataset with key variables from credible websites, the Bagging Classifier algorithm demonstrated a substantial improvement, achieving an accuracy rate of 98.4% resulting in a significant enhancement in phishing website detection compared to other methods. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Harnessing Transformative Potential of UAV-Based AI-Powered Data Analysis for Emission Monitoring 6

Harnessing Transformative Potential of UAV-Based AI-Powered ...

引用

6th International Conference on Computational Intelligence and Networks, CINE 2024

作者： Namdev, Mayank Dholaria, Jay Rathi, Meet Manipal University Dept. of Computer Science Engineering Jaipur India

ISBN: (纸本)9798331516796

With the growing pressure to reduce environmental pollution, the combination of Unmanned Aerial Vehicles (UAVs) and Artificial Intelligence (AI) offers a viable path forward for modernizing emission monitoring. This research investigates the revolutionary potential of UAV-based AI-powered data analysis for emissions monitoring, with a particular emphasis on the comparison of XGBoost and CatBoost algorithms. Real-time monitoring, identification, and analysis of pollutants can now be done with remarkable accuracy and efficiency thanks to UAVs outfitted with modern sensors and AI algorithms. This novel methodology has significant advantages over typical monitoring approaches, including increased spatial coverage, lower costs, and higher data quality. Furthermore, AI integration provides predictive analytics and anomaly identification, allowing for proactive environmental risk mitigation interventions. Despite its enormous promise, challenges such as regulatory frameworks, privacy concerns, and technological restrictions must be solved before widespread usage. Overall, the combination of UAVs and AI, as well as the comparison of XGBoost and CatBoost, hold enormous promise for revolutionizing emission monitoring by providing a scalable and versatile solution to protect environmental quality and human health. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

A Review on Cosmetic Product Recommendation Using Deep Learning 4

A Review on Cosmetic Product Recommendation Using Deep Learn...

引用

4th International Conference on Soft Computing for Security Applications, ICSCSA 2024

作者： Chouhan, Ruchika Barde, Snehlata Sage University Dept. of Computer Science Engineering Indore India

ISBN: (纸本)9798331515720

Cosmetic products play an important role in every one's life. Cosmetic products also called as makeup are substance that is applied on the body especially on face. The modern lifestyle can be demanding, leaving little time for self-care. However, it's crucial to prioritize self-care, including skincare, despite hectic schedules. Indeed, relying solely on best-seller products or in-store recommendations may not always be effective in determining compatibility between a skincare product and an individual's skin condition. This is because everyone's skin tone and type of the skin is unique, with varying sensitivities, concerns, and needs. Many people buy their goods online today, using various e-commerce sites. So, to choose the best skincare product during online purchasing is difficult, since it depends entirely on skin type and usage. The main aim of this paper is to survey and explores the existing recommendation systems designed to assist users in selecting cosmetics personalized to their unique skin type, by using advanced algorithms and machine learning. This study has reviewed various methods like face recognition, cosmetic product recognition, tag recommendation, facial skin image classification using convolution neural network, a new examples-rules guided deep neural network approach. Through a comprehensive review of literature and existing research, this paper examines the methodologies, algorithms, and techniques employed in cosmetic recommendation systems. Key factors such as user preferences, skin type, skin concerns, and product attributes are analysed to understand how recommendation systems use this information to generate personalized recommendations. © 2024 IEEE.

关键词： Cosmetics

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

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：