检索结果-内蒙古大学图书馆

4th International Conference on Power, Energy, Control and Transmission Systems, ICPECTS 2024

作者： Deepika, R. Monish, J. Daniel Felix, V. Bharath Kumar, A. Sri Sairam Engineering College Department of Computer Science & Engineering Chennai India

ISBN: (纸本)9798331508845

Unofficially, Agriculture is now considered to be one of the least profitable jobs one could do. The main reason behind this is that the livelihood of farmers which is based on the only source of their income is being affected. Most of their income is decided by the Intermediates. The price of the cultivated crops is being decided by the third parties rather than being decided by Farmers itself. An application to overcome the existing intermediate system in the field of agriculture by connecting farmers with consumers directly through this app can provide a solution the above problem. Giving the control of fixing the price of harvested products by the farmers itself through this app can help solving the abovementioned problem. Our idea is to create an AI based Application that provides a direct link between the customers and the cultivators, which helps the farmers to decide their price for their products with a reasonable amount of profit. By this, customers can directly avail products from farmers for a reasonable price. Our target are the cities near cultivable lands, where we establish a hub for storing and delivering goods. Customers can either pick up their orders directly from these hubs or opt for door delivery. This App contains personalised User Interface (UI)for both Farmers and Consumers. That works on the principle inspired from REVERSE BIDDING. Also have included features such as Artificial Interface (AI) based recommendations of products, user friendly chatbots. © 2024 IEEE.

关键词： Artificial Intelligence E-Commerce Farming Reverse Bidding

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Recognition of Handwritten Devanagri Character 1

Machine Learning for Recognition of Handwritten Devanagri Ch...

引用

1st International Conference on Computing, sciences and Communications, ICCSC 2024

作者： Tyagi, Shilpa Dutta, Chiranjit Singh, Manu SRM Institute of Science and Technology Department of Computer Applications Uttar Pradesh Ghaziabad201204 India SRM Institute of Science and Technology Department of Computer Science & Engineering Uttar Pradesh Ghaziabad201204 India ABES Engineering College Department of Computer Science Uttar Pradesh Ghaziabad India

ISBN: (纸本)9798350353648

A framework known as optical character recognition is capable of converting handwritten or printed pictures into machine-editable structures. Several Indian dialects, including Hindi, Nepali, Marathi, Sindhi, and others, use the Devanagari script. In India, Hindi is the national language and the language that is spoken by most people. This script organises the development of the language. Nowadays, people are interested in gathering data in sophisticated configurations that are available in paper archives and then employing a search process to reuse this data later. In this study, we provide a novel approach to Devanagari script character recognition for printed Hindi characters. The principal objective of this research is to identify the consonants and the vowels, which can subsequently be used for recognizing the complicated inferred words. The primary focus of this project is on the identification of each individual consonant and vowel. Several pre-processing techniques, including feature extraction, segmentation, and classification, have been researched and used in this project to create an advanced Hindi OCR system. The K-NN classification technique was used in earlier research;however, in the work that is being suggested, we have employed a hybrid technique that combines neural networks with K-NN. The recognition rate of the suggested approach is 97.4%, whereas that of the existing techniques is 94.5%. This suggests that the approach which proposed here is superior to techniques employed in the method which already exist. © 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

Crop Yield Prediction Using Multimodal Meta-Transformer and Temporal Graph Neural Networks

IEEE Transactions on AgriFood Electronics

引用

IEEE Transactions on AgriFood Electronics 2024年第2期2卷 545-553页

作者： Sarkar, Somrita Dey, Anamika Pradhan, Ritam Sarkar, Upendra Mohan Chatterjee, Chandranath Mondal, Arijit Mitra, Pabitra Indian Institute of Technology Kharagpur Centre for Computational and Data Sciences Kharagpur721302 India Indian Institute of Technology Kharagpur Department of Industrial and Systems Engineering Kharagpur721302 India Indian Institute of Technology Kharagpur Department of Agricultural and Food Engineering Kharagpur721302 India Indian Institute of Technology Patna Department of Computer Science and Engineering Patna801106 India Indian Institute of Technology Kharagpur Department of Computer Science and Engineering Kharagpur721302 India

Crop yield prediction is a crucial task in agricultural science, involving the classification of potential yield into various levels. This is vital for both farmers and policymakers. The features considered for this task are diverse, including weather, soil, and historical yield data. Recently, plant images captured in different modalities, such as red-green-blue, infrared, and multispectral bands, have also been utilized. Most of these data are inherently temporal. Integrating such multimodal and temporal data is advantageous for yield classification. In this work, a deep learning framework based on meta-transformers and temporal graph neural networks has been proposed to achieve this goal. Meta-Transformers allow the modeling of multimodal interactions, while temporayel graph neural networks enable the utilization of time sequences. Experimental results on the publicly available EPFL multimodal dataset demonstrate that the proposed framework achieves a high classification accuracy of nearly 97%, surpassing other state-of-the-art models, such as long short-term memory networks, 1-D convolutional neural networks, and Transformers. In addition, the proposed model excels in accuracy metrics, with a precision of approximately 98%, an F1-Score of 91%, and a recall of 94% in crop yield prediction. © 2024 IEEE.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

MRI Scans for Deep Learning-Based Chronic Nephropathy Detection: A Comparison of CNN, MobileNet, VGG16, and ResNet-50 Models 5

MRI Scans for Deep Learning-Based Chronic Nephropathy Detect...

引用

5th IEEE International Conference for Emerging Technology, INCET 2024

作者： Amanatulla, M.D. Swathi, G. Pallavi, M. Bindu, K. Pavana Computer Science & Engineering Department Lakkireddy Balireddy College of Engineering Mylavaram India

ISBN: (纸本)9798350361155

Prolonged Nephropathy Given that detection usually shows no signs in its early phases and has a high morbidity rate, it presents a serious danger to world health. This research paper proposes a machine learning architecture that uses models based on deep learning (CNN, MobileNet, VGG16, ResNet-50) to identify illness using MRI data. 12, 446 images in the dataset obtained through Kaggle are categorized as normal, cyst, stone, and malignancy. The study evaluates the models' performances, and ResNet-50 exhibits the highest accuracy. The VGG16 and ResNet-50 designs for the proposed system are presented, with a focus on their characteristics. Pre-processing, instruction, classification, and collection of data are all included in the implementation. Users may upload their photos to be classified by different algorithms. The results demonstrate the effectiveness of the ResNet-50 model, which had an overall 98% classification accuracy for renal diseases. In conclusion, the application of deep learning specifically, the ResNet-50 model shows promise as a quick and dependable technique for detection, therefore alleviating a major healthcare issue. © 2024 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Graph-Based Anomaly Detection Using Variational Autoencoder 24

Unsupervised Graph-Based Anomaly Detection Using Variational...

引用

24th IEEE International Conference on data Mining Workshops, ICDMW 2024

作者： Sadrolhefazi, Zeinab Sadat Zare, Hadi Asghari, Seyyed Amir Moradi, Parham Jalili, Mahdi University of Tehran Department of Data Science and Technology Tehran Iran Kharazmi University Department of Electrical and Computer Engineering Tehran Iran RMIT University School of Engineering Melbourne Australia

ISBN: (纸本)9798331530631

Anomaly detection is recognized as a critical task in machine learning, particularly when applied to high-dimensional and graph structured data. Traditional clustering based methods for anomaly detection are often challenged by such settings. In this paper, by leveraging Variational Graph Autoencoders (VGAEs) a new method is proposed to embed graph-structured data into a low-dimensional latent space, thereby enhancing anomaly detection through unsupervised learning. Synthetic labels, generated via spectral clustering, are incorporated to enable the model to learn from the intrinsic structure of the graph while improving cluster separability in transductive learning settings. Additionally, a dynamic early stopping mechanism based on Exponential Moving Average (EMA) is introduced to optimize training duration. Extensive experimental results demonstrate that VGAEs outperform earlier works in terms of accuracy and efficiency, particularly when applied to complex, noisy, and high-dimensional datasets. By combining deep learning with clustering, the proposed approach offers potential applications in areas such as healthcare and social network analysis, where the detection of anomalies and clustering of complex data are essential. By embedding graph data into meaningful clusters, this work addresses the challenges posed by high-dimensional and sparse data, contributing to the advancement of deep clustering models. © 2024 IEEE.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

FinSecure: Utilizing IoT Sensors for Formaldehyde Detection and Fish Freshness Detection for Enhancing Safety in Fish Consumption Using Machine Learning and Deep Learning

FinSecure: Utilizing IoT Sensors for Formaldehyde Detection ...

引用

2024 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication, IConSCEPT 2024

作者： Harish, S. Somesh, K. Suntharavadivelan Venkatesan, M. Prabhavathy, P. National Institute of Technology Puducherry Department of Computer Science and Engineering Karaikal India Vellore Institute of Technology Department of Computer Science and Engineering and Information Systems Vellore India

ISBN: (数字)9798331540685

ISBN: (纸本)9798331540685

The global food supply heavily relies on fisheries, highlighting the crucial importance of ensuring the safety of fish products. However, the widespread application of antibiotics and the existence of compounds such as formaldehyde present significant hazards to both human consumers and the underwater ecosystem. These risks are compounded by processes like bio-magnification, further emphasizing the need for vigilant monitoring and regulation. This project presents a comprehensive approach to fisheries management and food safety monitoring through the integration of advanced machine learning, deep learning techniques and IoT sensor technology. The overall objective is to develop a model that can determine whether the given sample Fish Species is safe or unsafe for human consumption, by considering parameters: Fish Freshness Detection, using a HCHO Sensor to determine the Formaldehyde levels in the given Fish and finally using these parameters to determine whether the fish can be consumed or not. For the Fish Freshness Detection, utilizing Transfer Learning (pre-trained MobileNetV2 model), the system achieves an impressive accuracy of 99.02%. Thus, integrating all these models, determine whether the supplied fish is safe for consumption or not. By integrating these functionalities, the system contributes to proactive fisheries and food safety monitoring and protection. The holistic approach of this project, combining accurate positions the developed model and IoT application as valuable assets for sustainable aquaculture practices and the preservation of aquatic ecosystems. The project's outcomes contribute to the advancement of several interdisciplinary domains such as machine learning, and fisheries management, laying the groundwork for continued innovation in this interdisciplinary domain. © 2024 IEEE.

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

Development of Blockchain-Enabled E-Healthcare Appointment System 5th

Development of Blockchain-Enabled E-Healthcare Appointment S...

引用

5th International Conference on Trends in Computational and Cognitive engineering, TCCE 2023

作者： Rawat, Abhishek Suryavanshi, Raghuraj Singh Nagar, Vishal Yadav, Divakar Department of Computer Science and Engineering Pranveer Singh Institute of Technology Uttar Pradesh Kanpur India Department of Computer Science and Engineering Institute of Engineering and Technology Uttar Pradesh Lucknow India

ISBN: (纸本)9789819719228

The adoption of the technology of smart contracts to construct an e-appointment system has an array of advantages over conventional appointment systems. E-appointment system commitments can be instantly conducted and reported using blockchain, removing the requirement for mediators and the possibility of fraud. In this paper, a framework is implemented in Remix IDE by using the smart contract that manages agreements between the user and the healthcare service provider. The E-appointment system will be able to privately and openly manage end-users using Ethereum, with terms and conditions enforced automatically via the smart contract. This work has the potential to significantly disrupt the centralized appointment system because it provides a safer and more effective alternative to conventional appointment scheduling methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Enhancing Fire Safety: Encoder-Decoder Based Detection and IoT-Driven Response System 2

Enhancing Fire Safety: Encoder-Decoder Based Detection and I...

引用

2nd International Conference on Information and Communication Technology, ICICT 2024

作者： Roy, George Tonmmoy Atik, Atiqul Islam Rabby, Masudur Rahman Islam, Md. Repon Department of Computer Science and Engineering Khulna University of Engineering and Technology Khulna Bangladesh

ISBN: (纸本)9798331508227

Innovative technologies are crucial for improving fire detection and response systems. An embedded system has been developed to improve fire detection and response by integrating a user mobile application, an admin website, and an IoT-based robot. The mobile application uses the Encoder-Decoder architecture to identify fires from user-captured images, enabling real-time transmission of critical data via the Firebase Realtime database. The encoder-decoder model performs better with an accuracy of 97.50%, precision of 97.20%, recall of 97.10%, and F1-score of 97.05%. The admin website serves as a centralized management platform, utilizing Google Maps API for real-time robot tracking and video streaming from the robot’s camera. The system also employs fire and person detection(YOLOv4) algorithms for enhanced monitoring. The robot’s construction includes fireproof materials for resilience in fire-prone environments. This comprehensive system offers a robust solution for effective fire detection and response, improving safety and efficiency in emergencies. ©2024 IEEE.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

An Android App for Ayurvedic Herb Identification and Classification Using Machine Vision 1

An Android App for Ayurvedic Herb Identification and Classif...

引用

1st International Conference on Trends in engineering Systems and Technologies, ICTEST 2024

作者： Vinod, Devi Simon, Santhosh Radhakrishnan, Anuja Jacob, Pramod Mathew Dilhaque Ahemmed, C.P. Adwaith, M. Mathew, Nithin Providence College of Engineering Department of Computer Science and Engineering Kerala Chengannur India

ISBN: (纸本)9798350307795

Kerala, a southwestern state in India, is renowned for its rich tradition of Ayurveda, an ancient system of holistic healing. However, it was a major concern regarding difficultly in identification of medical herbs. It is not possible for a naive user to confirm whether the identified leaf is correct or not. So, we propose an Android app-based solution for this problem. The app scans the herb leaf image and can promptly provide information about the herb's name, medicinal properties, and display the success rate of identification. The proposed system employs a comprehensive dataset of Ayurvedic plant leaves, enabling it to accurately classify and identify plant species. By harnessing the power of deep learning through computer Vision technique, the model extracts intricate features from leaf images, while machine learning algorithms refine the classification process which identifies the scanned leaf. The outcome is a robust, user-friendly mobile application which can be used anywhere in world to scan and identifies the leaves. © 2024 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Application in PQRS Segment Detection in ECG data

Deep Learning Application in PQRS Segment Detection in ECG D...

引用

2024 International Conference on Electrical, Electronics and Computing Technologies, ICEECT 2024

作者： Pandey, Amit Kumar Gupta, C.L.P. Bansal Institute of Engineering and Technology Department of Computer Science and Engineering Lucknow India

ISBN: (纸本)9798350378092

The electrocardiogram is a vital piece of information about a person's health that provides measurements of changes in the cardiovascular system. When using complex software modules to diagnose diseases, the clinical ECG signal is always tainted by power line interference and electromagnetic fields, leading to inaccurate ***, it's critical to reduce these ECG data acquisition recording inaccuracies in order to perform precise clinical analysis. We are working on an algorithm that will split the data array of three successive ECG signals into three equivalents. The Empirical Mode After decomposing the data matrix and running it through the Independent Component Generation algorithm, we will identify and remove any noisy components using deep learning scheme. To obtain an error-free result of ECG data, we will then apply reverse ICA and EMD features for deep learning. © 2024 IEEE.

关键词： Deep learning

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

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

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：