检索结果-内蒙古大学图书馆

Enhancing Plant Leaf Disease Prediction Through advanced Deep Feature Representations: A Transfer Learning Approach

Journal of The Institution of Engineers (India): series B 2024年第3期105卷 469-482页

作者： Naralasetti, Veeranjaneyulu Bodapati, Jyostna Devi Department of Information Technology Vignan’s Foundation for Science Technology and Research Guntur India Department of Advanced Computer Science and Engineering Vignan’s Foundation for Science Technology and Research Guntur India

Plant diseases present a considerable threat to the farming industry, causing significant economic losses by reducing crop yields. The emergence of deep neural network models in the realm of computer vision has brought about a groundbreaking transformation in the swift recognition and surveillance of plant diseases. In this study, we introduce an innovative approach for plant disease prediction, leveraging transfer learning techniques to enable accurate and early detection of plant diseases. The proposed leaf disease prediction framework encompasses multiple key stages, including preprocessing, feature extraction, classification, and postprocessing. Notably, our model excels at feature extraction, utilizing the pre-trained convolutional architecture of VGG16 to extract valuable information from leaf images. These features are then fed into a deep neural network model designed for disease prediction. The feature extraction method employed in our approach excels at capturing intricate disease-related details from plant images. When the deep features extracted are utilized for classification using our proposed classifier, the outcome demonstrates a substantial enhancement in disease prediction performance. Based on extensive experimentation with the benchmark plant village dataset, it is evident that our transfer learning-based approach outperforms existing methods, achieving an impressive accuracy rate of 96.56%. Besides accuracy, the proposed approach surpasses F1_score and Kappa scores for the benchmark plant village dataset. © The Institution of Engineers (India) 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Two-stage Deep Learning Approach for Optimizing Fashion Product Recommendations

引用

sN computer science 2025年第4期6卷 1-13页

作者： Buradagunta, suvarna Balakrishna, sivadi Department of Computer Science and Engineering Vignan’s Foundation for Science Technology and Research Guntur India Department of Advanced Computer Science and Engineering Vignan’s Foundation for Science Technology and Research Guntur India

Online shopping platforms are experiencing rapid growth, necessitating effective product recommendation systems to enhance customer satisfaction by recommending visually similar products. Traditional statistical techniques often result in less accurate recommendations. This study encompasses two primary tasks: Query Product Classification and Product Recommendation Retrieval. The initial job employs a Deep Neural Network, which takes high-level feature representations derived from the Xception and VGG16 for the query image. The features are further analyzed to forecast the category of the product. The second step is retrieving analogous products by calculating cosine similarity, facilitating the identification of visually comparable items within the product database. By leveraging diverse feature representations, the proposed approach improves the precision and relevance of recommendations. Experimental evaluations on fashion product images and shoe datasets demonstrate significant performance improvements over existing models, achieving accuracies of 91.76%, and 82.23% respectively. These results underscore the capability of the system to provide superior recommendations in online fashion shopping scenarios, emphasizing its effectiveness in improving customer experience. © The Author(s), under exclusive licence to springer Nature singapore Pte Ltd. 2025.

关键词： Content-based recommendation Image based recommendation system Pretrained models Recommendation systems VGG-16 Visual product recommendation Xception

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Multi-modal Approach for Enhanced Product Recommendations Based on Customer Habits

引用

Journal of The Institution of Engineers (India): series B 2024年第6期105卷 1537-1545页

作者： Bodapati, Jyostna Devi Veeranjaneyulu, N. Yenduri, Lakshmana Kumar Advanced Computer Science and Engineering Vignan’s Foundation for Science Technology and Research Andhra Pradesh Guntur India Department of IT Vignan’s Foundation for Science Technology and Research Vadlamudi522213 India San Francisco Bay Area United States

In response to the evolving demands and challenges in recommendation systems, a comprehensive and innovative approach is proposed for delivering personalized and accurate product recommendations while mitigating existing limitations. This approach combines cutting-edge methodologies from collaborative filtering, content-based recommendation systems, and state-of-the-art deep learning architectures to enhance the standard of recommendations and improve user contentment. The hybrid approach encompasses various modules, including data preprocessing, feature engineering, deep learning model development, recommendation generation processing, and post-processing. Utilizing the H &M Fashion dataset, a rich collection of product images and metadata, for experimentation, the dataset undergoes preprocessing to ensure data quality, and features are extracted from both text and images using transfer learning approaches. These features are then integrated into a unified representation using fusion techniques. subsequently, a deep learning model is developed to generate personalized recommendations based on the integrated features. Empirical findings on benchmark H &M dataset demonstrate the superiority of the proposed hybrid approach over traditional content-based and collaborative-based models, with improvements in accuracy, recall, and F1 score. The hybrid model effectively combines different recommendation techniques, offering robustness, adaptability, and enhanced recommendation quality. This research contributes to the advancement of recommendation systems, offering insights and solutions for delivering tailored recommendations in the fashion retail industry. © The Institution of Engineers (India) 2024.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Multi-label text classification using adaptive promptify concepts 15

Enhancing Multi-label text classification using adaptive pro...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Reddy, Veerababu Uppukonda, Usha Rani Veeranjaneyulu, N. Vignan's Foundation for Science Technology & Research Dept. of Computer Science & Engineering Guntur India Vignan's Lara Institute of Technology & Science College Dept. of Computer Science & Engineering Guntur India Vignan's Foundation for Science Technology & Research Dept. of Information Technology Guntur India

ISBN: (纸本)9798350370249

In present days, Multi Label Text Classification (MLTC) has become an important research area in Natural Language Processing (NLP). Existing models of MLTC have been facing domain specificity and fine-tuning challenges. Hence a model is developed to overcome the above said challenges by introducing Prompt engineering, GPT FineTuning methods and Pipeline algorithms. The experimental results are obtained based on the present Generative pre trained data produces labels for various text documents and files with an exceptional accuracy of 85%. The outcomes of the experiments reveal notable enhancements over the baseline models. © 2024 IEEE.

关键词： Fine-Tuning GPT Multi-Label Text classification NLP (Natural Language Processing) Pre-trained models Prompt engineering Transformers

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Multi-Class Classification Models for Obesity Risk Prediction

Comparative Analysis of Multi-Class Classification Models fo...

引用

2024 IEEE International Conference on Modeling, simulation and Intelligent Computing, MosICom 2024

作者： Naik, Ds Bhupal Afrin, Mohammad salafsha Rao, P srinivasa Reddy, Bhavanam Amarendra Advanced Computer Science and Engineering Vignan's Foundation for Science Technology and Research Guntur India

ISBN: (纸本)9798331533311

Obesity is a global health issue associated with increased risks of various chronic diseases, such as diabetes, cardiovascular disease, and certain cancers. Accurate prediction of obesity risk can enable early interventions, improve patient outcomes, and alleviate healthcare burdens. This study performs a comparative analysis of several multiclass classification models to predict obesity risk levels based on demographic, lifestyle, and health-related features. we aimed to predict obesity risk in individuals using various machine learning algorithms, with a particular focus on the Light Gradient Boosting Machine (LGBM) classifier. Obesity is a growing global health issue linked to numerous serious diseases. We evaluated several algorithms, including LGBM, Random Forest, Decision Tree, support Vector Classifier (sVC), Logistic Regression, and AdaBoost algorithms to determine their effectiveness in accurately classifying obesity risk. Our findings revealed that the LGBM classifier outperformed the others with an impressive accuracy of over 9 0%. Random Forest followed closely, while Decision Tree, sVC, Logistic Regression, and AdaBoost showed progressively lower accuracies. The LGBM algorithm's superior performance highlights its potential as a valuable tool for early obesity risk detection and intervention, enabling healthcare providers to take proactive steps in managing and preventing obesity. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

An Extensive Review of Intelligent Deep Learning Based Anomaly Detection and Classification of 3D MRI Brain Imaging Data 3

An Extensive Review of Intelligent Deep Learning Based Anoma...

引用

3rd International Conference on sentiment Analysis and Deep Learning, ICsADL 2024

作者： Hima Bindu, J. Uma Dev, M. Vignan's Foundation for Science Dept. of Computer Science and Engineering Andhra Pradesh Guntur522213 India

ISBN: (纸本)9798350396157

MRI - Magnetic Resonance Imaging is one of the frequently employed imaging modalities for brain anomaly detection. MRI produces a massive quantity of data, which includes a consecutive set of scans taken at several time instants. since the existence of brain anomalies that exists examined on every MR sequence, manual brain anomaly detection necessitates anatomical knowledge, costly, laborious, and inaccurate due to human error. Automatic brain anomaly segmentation from 3D Magnetic Resonance Image (MRI) is essential to perform proper diagnosis, monitoring, and treatment planning of the disease. However, owing to the structural difficulties such as hazy boundaries with uneven shapes, precise 3D brain tumor demarcation is interesting. With the recent developments of Deep Learning (DL) models, this research study reviews the recent brain anomaly detection and classification models based on DL approach with 3D MRI data. The existing techniques related to brain tumor segmentation, classification, and validations are reviewed. Every reviewed technique is investigated based on the aim, underlying technique used, dataset, and evaluation parameters. Besides, a comparison table is provided by summarizing the reviewed techniques under several aspects. Finally, a quick analysis of the evaluated techniques' results is conducted to gauge their effectiveness. © 2024 IEEE.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Exploring Deep Learning Techniques for Automated Cataract Detection in Digital Camera Imagery

Exploring Deep Learning Techniques for Automated Cataract De...

引用

2024 International Conference on Advances in Modern Age Technologies for Health and engineering science, AMATHE 2024

作者： Kamepalli, sujatha Veeranjaneyulu, N. Bodapati, Jyostna Devi Vignan's Foundation For Science Technology And Research Dept. Department Of Information Technology And Computer Application Guntur India Vignan's Foundation For Science Technology And Research Dept. Department Of Advnced Computer Science And Engineering Guntur India

ISBN: (纸本)9798350371567

Cataracts, a prevalent eye condition impacting vision, demand accurate and prompt identification for effective risk reduction and blindness prevention. Traditional methods of cataract diagnosis rely heavily on manual examination by ophthalmologists, which can be time-consuming and subject to human error. With the advent of digital imaging technology, there is an opportunity to enhance the efficiency of cataract detection. The deep neural network models VGG19 and ResNet-50 are recommended in this paper for automatic cataract identification on digital camera images. To optimize network performance, adjustments to loss and activation functions were made, incorporating minimal kernels, reduced training parameters, and layers. This resulted in a ResNet-50 model with significantly decreased computational cost and average operating time compared to the cutting-edge models. The proposed ResNet 50 model achieved an average accuracy of 93.41%, outperforming the VGG 19 model, which had an accuracy of 91.13%. This research contributes to the evolution of cataract detection methodologies, emphasizing the potential of deep learning models, particularly ResNet-50, in improving diagnostic accuracy and operational efficiency for enhanced eye health outcomes. © 2024 IEEE.

关键词： Digital cameras

来源：评论

学校读者我要写书评

暂无评论

Youtube Transcript summarizer 5

Youtube Transcript Summarizer

引用

5th International Conference on Mobile Computing and sustainable Informatics, ICMCsI 2024

作者： Panthagani, Vijaya Babu Duggempudi, Vijaya Deepika Reddy Kommera, Naga Lakshmi Vakkalagadda, Nikhita Vignan's Foundation for Science Technology and Research Dept. Computer Science and Engineering A.P Guntur India

ISBN: (纸本)9798350395235

In the modern world, a video transcript summarizer offers a wide range of applications. It draws attention to the crucial points in the video. YouTube videos are watched in large quantities by people for a variety of reasons, including enjoyment, education, obtaining crucial information, and pursuing personal hobbies. Finding a video with any meaningful information about a subject is incredibly tough because most videos are just buffers for unimportant information. The main goal in the majority of situations is to get useful information from the video. In order to generalize YouTube video transcripts for abstractive text summary without sacrificing the essential details and substance, this research has developed a video summarization system based on Natural Language Processing and Machine Learning. The goal of this project is to make the writing for the videos shorter. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

An Efficient Approach for semantic segmentation of salt Domes in seismic Images Using Improved UNET Architecture

引用

Journal of The Institution of Engineers (India): series B 2023年第3期104卷 569-578页

作者： Bodapati, Jyostna Devi sajja, RamaKrishna Naralasetti, Veeranjaneyulu Department of Advanced Computer Science and Engineering Vignan’s Foundation for Science Technology and Research Vadlamudi India IAENG Life Member Andhra Pradesh Guntur India Department of Information Technology and Computer Applications Vignan’s Foundation for Science Technology and Research Vadlamudi India

Many areas of Earth’s surface with large accumulations of gas and oil even have huge deposits of salt under the surface. Exploring such deposits helps many countries to increase the storage capacity of their Petroleum reserves and explore new ones. But finding such deposits is a herculean task. Expert seismic imaging requires human interpretation of salt bodies. But this leads to very biased and highly variable translations. so the idea behind this paper is to build an approach that accurately and automatically identifies if the seismic image contains any region of salt deposit or not. If a surface is found to have salt deposits, then it may contain the accumulations of oil or gas and even the salt domes or caverns can be used as a storage site for already available petroleum or oil. since semantic segmentation classifies every pixel in the given image to its class label, this can be used to segment the salt deposits from the provided seismic images. In this paper, we introduce a variation of UNet, a popular segmentation model, for seismic image segmentation. We have added a batch normalization layer following every convolution layer as a deeper network helps extract better features which turned out to be true. some interesting findings of this work are that the augmentation works well as this avoids over-fitting of the model. sharpening as a post-processing technique has come up with a considerable amount of rise in the performance. Here, we prefer to use the metric as Intersection over Union (IoU) instead of accuracy as it is not as affected by the class imbalances that are inherent in foreground/background segmentation tasks. With the proposed methodology, we achieve an averaged IoU of 85.6 which is far better compared to the IoU achieved with the segnet approach which stands at 77. © 2023, The Institution of Engineers (India).

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

CNN Models Transfer Learning Based ship Classification for Intelligent ship Routing

CNN Models Transfer Learning Based Ship Classification for I...

引用

2024 IEEE International Conference on computer Vision and Machine Intelligence, CVMI 2024

作者： Tiwari, Brij Kishor Munagala, Rohini sai Mannarugudi, sai Dheeraj Vignan's Foundation for Science Technology and Research Department of Advanced Computer Science and Engineering Guntur522213 India

ISBN: (纸本)9798350376876

Collision free autonomous navigation is challenging area of interest for the shipping industry, and an accurately classifying the ships according to their size and type classes is a crucial undertaking in marine operations. Accurate prediction and identification will improve the maritime security and navigation safety. However, automatic ship classification is a difficult subject because of the wide variety of ship designs and the complexity of visual data. We developed a deep learning model using transfer learning from pre-trained models in order to classify five different kinds of ships. We performed the experiment using different pre-trained convolution neural network model of the deep learning. In the transfer learning we considered the training of the dataset for 100 epochs. In this study, we investigated four deep learning model ResNet 50, VGG 16, VGG 19, and Inception V3. We carried out the identical procedure for training of each model by removing the top layer of pre-trained model and adding three dense layers for the top layers. The neuron counts are 1024, 512, 256 respectively followed by dropout layer of 0.5. Results of our model shows the maximum obtained accuracies are 86.66 % and from these we can observed that the developed model can be used for ship identification and classification and to take the decisions for collision free and smooth navigation. © 2024 IEEE.

关键词： Transfer 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

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：