检索结果-内蒙古大学图书馆

Developing an Integrated IoT Cloud Based Predictive Conservation Model for Asset Management in Industry 4.0

Journal of Social Computing 2023年第2期4卷 139-149页

作者： Karnam Shanmugam Kachhti Satyam Thimma Reddy Sreenivasula Reddy the Department of Computer Applications Annamacharya Institute of Technology and SciencesKarakambadiTirupathi 517520India the Department of Computer Science and Engineering Annamacharya Institute of Technology and SciencesKarakambadiTirupathi 517520India

With the advent of Industry 4.0(I4.0),predictive maintenance(PdM)methods have been widely adopted by businesses to deal with the condition of their *** the help of I4.0,digital transformation,information techniques,computerised control,and communication networks,large amounts of data on operational and process conditions can be collected from multiple pieces of equipment and used to make an automated fault detection and diagnosis,all with the goal of reducing unscheduled maintenance,improving component utilisation,and lengthening the lifespan of the *** this paper,we use smart approaches to create a PdM planning *** five key steps of the created approach are as follows:(1)cleaning the data,(2)normalising the data,(3)selecting the best features,(4)making a decision about the prediction network,and(5)producing a *** the outset,PdM-related data undergo data cleaning and normalisation to get everything in order and within some kind of *** next step is to execute optimal feature selection in order to eliminate unnecessary *** research presents the golden search optimization(GSO)algorithm,a powerful population-based optimization technique for efficient feature *** first phase of GSO is to produce a set of possible solutions or objects at *** objects will then interact with one another using a straightforward mathematical model to find the best feasible *** to the wide range over which the prediction values fall,machine learning and deep learning confront challenges in providing reliable *** is why we recommend a multilayer hybrid convolution neural network(MLH-CNN).While conceptually similar to VGGNet,this approach uses fewer parameters while maintaining or improving classification correctness by adjusting the amount of network modules and *** projected perfect is evaluated on two datasets to show that it can accurately predict the future state of components for upkeep prepara

关键词： Industry 4.0 predictive maintenance golden search optimization multilayer hybrid convolution neural network data cleaning

来源：评论

学校读者我要写书评

暂无评论

Advertisement Image Classification Using Deep Learning with BERT: A Novel Approach Exploiting Textual Features

Advertisement Image Classification Using Deep Learning with ...

引用

International Conference on Data Analytics and Management, ICDAM 2023

作者： Jain, Pooja Taneja, Kavita Taneja, Harmunish Department of Computer Science and Applications Panjab University Punjab Chandigarh160014 India Department of Computer Science and Information Technology DAV College Punjab Chandigarh India

ISBN: (纸本)9789819965465

Newspapers are an important source for job postings, admission notices, tender announcements, sales and promotions, and many other advertisements. However, there are no category-wise search capabilities for advertisements in either the printed versions or the online versions of the newspapers. This category-wise advertisement retrieval requires a classification model that can classify advertisement images into different predefined advertisement classes. This research study presents and compares two advertisement image classification models which use deep learning for advertisement analysis, understanding, and classification thereafter. Two datasets including Advertisement Image Dataset and a corresponding Advertisement Text Dataset have been created to enable this research. The first classification model presented in this study is a common approach of using convolutional neural network (CNN)-based image classification model in which a pretrained residual network with 50 layers (ResNet50) model is fine-tuned on visual (image only) features using Advertisement Image Dataset giving 70.8% accuracy. The second classification model is a novel approach for advertisement image classification which exploits the textual features and fine-tunes pretrained bidirectional encoder representations from transformers (BERT) base model on Advertisement Text Dataset giving 96.7% accuracy. This significant improvement of 25.9% implies that exploiting textual features in advertisement image classification provides better image understanding leading to much higher classification accuracy than visual features. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Exploring AI Techniques for Yoga Image Classification: A Focus on Machine Learning and Deep Learning 1

Exploring AI Techniques for Yoga Image Classification: A Foc...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Duggal, Anjali Kumar, Satish Tripathi, Pooja Panjab University Department of Computer Science and Applications Chandigarh India Swami Sarvanand Giri Regional Centre Panjab University Department of Computer Science and Applications Hoshiarpur India Inderprastha Engineering College Aktu Department of Information Technology Lucknow India

ISBN: (纸本)9798331529246

Machine Learning (ML) has become essential for developing intelligent systems, providing critical Artificial Intelligence (AI) capabilities. ML involves teaching computers to solve problems by analyzing data, creating analytic models automatically, and performing associated tasks. Deep Learning (DL), a sophisticated branch of ML, utilizes neural networks to simulate AI and often surpasses traditional ML models and data analysis techniques, especially in applications like image classification. This study investigates ML and DL techniques with a particular focus on image classification applications. A novel experiment was conducted using the CNN and VGG16 model, with variations in batch size configurations to optimize yoga posture classification. The methodology involved a comprehensive review of existing approaches and experimental evaluation to assess the model's performance under different configurations. The experimental results demonstrated significant improvements in classification accuracy, achieving up to 86% in recognizing yoga postures. This represents a notable advancement in precision compared to existing methods, showcasing the effectiveness of DL models such as VGG16 in tackling complex image classification challenges. These findings underscore the potential of DL in achieving high accuracy in specialized domains like yoga posture recognition. The study provides a strong foundation for further research and application in related fields, highlighting the efficacy of advanced DL models in addressing domain-specific image classification problems. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Identification and Categorization of Paddy Leaf Diseases Using Deep Learning for Efficient Agricultural Practices

Identification and Categorization of Paddy Leaf Diseases Usi...

引用

2024 IEEE International Conference on Information Technology, Electronics and Intelligent Communication Systems, ICITEICS 2024

作者： George, Annie Sunil Devi, S. Vinita Sushila Hindustan Institute of Technology and Science Department of Computer Applications Tamil Nadu Chennai India

ISBN: (纸本)9798350382693

Plant diseases can be quickly detected to lessen the harm they cause to crops. Convolutional neural networks are widely used in deep learning, specifically for problems related to pattern recognition and machine vision. This paper aims to provide a comprehensive overview of the numerous image processing and machine learning strategies for rice plant disease diagnosis. It does this by examining the various algorithms and machine learning techniques used to diagnose illnesses in rice plants using photographs of diseased rice plants. This study discusses several methods and offers a concise synopsis of important concepts in the fields of machine learning and image processing in relation to the classification and identification of illnesses in rice plants. This study examines and contrasts various algorithmic models and methods for classifying and identifying diseases that impact rice plants. It includes scientific results that over the last five years have been published in international review publications. In addition, this paper presents an overview and analysis of various methods used to identify agricultural illnesses, leaf health, and the image processing techniques used for the same. The framework mentioned here, can be used to more effectively detect and diagnose various rice crop diseases, which can cause the agriculture industry to experience large losses owing to rice plant diseases. These frameworks are efficient enough to safely automate repeated processes, generating enough data for additional study. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

R2A-UNET: double attention mechanisms with residual blocks for enhanced MRI image segmentation

引用

Multimedia Tools and applications 2025年 1-31页

作者： Bentaher, Noura Lafraxo, Samira Kabbadj, Younes Ben Salah, Mohamed El Ansari, Mohamed Wakrim, Soukaina Department of Computer Science Faculty of Sciences Ibn Zohr University Agadir Morocco Informatics and Applications Laboratory Department of Computer Science Faculty of Sciences Moulay Ismail University Meknes Morocco Department of Radiology University Hospital of Agadir Faculty of Medicine and Pharmacy of Agadir Ibnou Zohr University Agadir Morocco

Gliomas, a highly aggressive and malignant category of brain tumors, continue to pose a significant global health challenge. Originating from the abnormal and uncontrolled growth of glial cells within the brain, these tumors often result in severe neurological impairments and high mortality rates, underscoring the urgency for improved diagnostic and therapeutic strategies. Early diagnosis can significantly improve outcomes and survival. Consequently, precise segmentation of tumor tissue in medical images is critical for accurate brain tumor diagnosis and effective treatment. However, achieving high-precision segmentation remains challenging due to the complex and variable nature of tumor structures in medical images. To address this problem, we developed R2A-UNET, a U-shaped architecture that leverages the power of residual blocks and attention mechanisms. To enhance the model’s ability to capture critical and relevant information, we incorporated two advanced attention mechanisms. These mechanisms are designed to prioritize important features while suppressing irrelevant or redundant details, thereby significantly improving the efficiency and accuracy of feature extraction across varying datasets. Normalized Channel Attention (NCA) was integrated in each encoder stage, generating a squeezed vector with relevant features at the end of the contracting path. Normalized Spatial Attention (NSA) was included in the skip connection in the middle of the encoder and decoder, generating more concentrated feature maps before concatenation on the decoder side. These mechanisms enable the model to focus on specific pixel values that more accurately localize abnormalities. In our study, we evaluated the performance of our model using two MRI image datasets: the LGG (Lower-Grade Glioma) segmentation database and the BraTS 2018 dataset. Our method achieved a DSC of 92% and an IoU of 86% on the LGG dataset. On the BraTS dataset, it achieved a DSC of 94.79% and an IoU of 90.12%, dem

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Stock Price Prediction using Modified BPSO for Feature Selection with RNN Variants on Top Tech Companies

Stock Price Prediction using Modified BPSO for Feature Selec...

引用

2023 IEEE World Conference on Communication and Computing, WCONF 2023

作者： Gupta, Priyank Paharia, Nitin Gupta, Sanjay Kumar Jadon, Rakesh Singh Jiwaji University SOS Computer Science and Applications Gwalior India Prestige Institute of Management and Research Department of Computer Applications Gwalior India MITS Department of Computer Science and Engineering Gwalior India

ISBN: (纸本)9798350311204

The most often utilized data in recent years is time series data, used for things like stock market price prediction and others. Recent research has focused chiefly on stock market prediction using neural networks, and new techniques are being developed to improve these models' accuracy. One such method uses optimization algorithms like PSO, GWO, or GA. Other variants, such as Binary-PSO and Binary-GWO, are developed by further enhancing the original algorithms. The paper suggested a variant of BPSO called MBPSO / TBPSO that assigned binary values to the features during optimization using the 'tanh' activation function. The TBPSO is then applied individually for two, five, and ten years to the datasets of five leading Tech firms. The dataset, which comprises a variety of historical and technical indicators, is applied to different variants of RNN and finds the best results with the GRU model to forecast the closing stock price. What transpired proves that, when used for prediction on the GRU model and when choosing more features than BPSO, TBPSO provides us with features that will provide more accuracy. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Analysis & Simulation of Student Learning System Amalgamated with Artificial Intelligent Algorithm 2

Analysis & Simulation of Student Learning System Amalgamated...

引用

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

作者： Bhatnagar, Ruchi Iimt University School of Computer Science and Applications Department Uttar Pradesh Meerut India

ISBN: (纸本)9798350360523

This IoT and AI are an envision technology for the smart higher education;which imparts depth knowledge and understanding. It is lifelong learning process where people develop their skills and knowledge as per need of social advancement and responsibility. As none of the aspect of life remains untouched with the smart technology so far higher education also. An IoT based numerous frameworks and applications are there to support higher education field and developed intellectual attitude towards smart things and encourage students to enhance their learning skills through such platforms. These smart digital platform enhances student's innate qualities as well as interest;and to provide them suitable learning process. In this research work we surveyed numerous IoT based applications used for higher education;their functionalities, concerned issues and challenges and proposal of an AI based predictive learning modular application system for university campus that facilitates students for outcome based learning and building important connections using app based modules;to redefined their success and shape their future as per industry need. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

IoT Based Agricultural Monitoring and Alert System 4

IoT Based Agricultural Monitoring and Alert System

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Priya, V Vishnu Nisanth, G. Dhanushree, D. Sindhu, M. Varshini, T. Preteka, A.T. Kongu Engineering College Department of Computer Science and Engineering Perundurai India Kongu Engineering College Department of Computer Applications Perundurai India Kongu Engineering College Department of Computer Technology Perundurai India

ISBN: (纸本)9798331523923

The goal of this project is to implement an Internet of Things (IoT)-based Agricultural Monitoring & Alert System (AMAS) that will integrate multiple sensors to continuously monitor agricultural parameters, such as soil moisture levels, soil temperature, water levels, irrigation pump operation status, and water quality, to improve precision farming practices. Enabling farmers to make well-informed decisions, maximize resources, and enhance crop output in real time is the primary objective of the AMAS system. The challenges of using IoT for agricultural monitoring, include issues with adoption among farmers, dependable technology, efficient data administration, and connectivity. Small-scale farmers' financial hardship and rural areas' restricted access to technology. Many obstacles stand in the way of the widespread adoption of IoT-based agricultural monitoring systems, such as smallscale farmers' limited financial resources, rural communities' restricted access to technology, and problems with connectivity, dependable data handling, and system scalability. Machine learning-based prediction models and IoT-integrated smart irrigation are two recent approaches that have showed promise in tackling these issues, but they still face obstacles such high implementation costs, technical complexity, and infrastructure dependence. By improving yields, increasing output, and facilitating remote monitoring, the AMAS system seeks to overcome these limits while taking into account the unique requirements and limitations of farmers. This study plan to enhance productivity, optimize yield, and implement remote monitoring. © 2025 IEEE.

关键词： Soil moisture

来源：评论

学校读者我要写书评

暂无评论

A Bio-Inspired Virtual Machine Placement Toward Sustainable Cloud Resource Management

引用

IEEE Systems Journal 2023年第3期17卷 3894-3905页

作者： Singh, Ashutosh Kumar Swain, Smruti Rekha Saxena, Deepika Lee, Chung-Nan National Institute of Technology Department of Computer Applications Kurukshetra136119 India Goethe University Department of Computer Science Frankfurt60323 Germany National Sun Yat-sen University Department of Computer Science and Engineering Kaohsiung804 Taiwan

Virtual machine placement (VMP) is the process of selecting the most appropriate physical machine (PM) to place users' requested virtual machine (VM) in large cloud data centers. Several methods have been framed to deal with this problem. However, the current solutions only consider limited resource types, resulting in an unbalanced load that activates unnecessary PMs inside the data center. In this article, we suggest a flower pollination-based nondominated sorting optimization (FP-NSO) algorithm that maximizes resource usage and minimizes energy consumption and carbon emission of the data center. Multiple resource-constraint metrics are associated with our algorithm that assists in finding the most suitable PMs for deploying VMs in a cloud environment. The VMP is carried out by employing the combined concept of flower pollination optimization and nondominated sorting technique-based genetic algorithm (NSGA-II). The algorithm is evaluated using the Google cluster dataset. The performance metrics like resource utilization, power consumption, and carbon emission values are computed for static and dynamic scenarios. The obtained results are compared with existing approaches. There is a significant reduction in power consumption, carbon emission, and execution time up to 16.69%, 48.60%, and 75.87%, respectively, and an improvement in resource utilization is up to 78.18%. © 2007-2012 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Various Machine Learning Models for Predicting Wheat Yield 2

Comparative Analysis of Various Machine Learning Models for ...

引用

2nd International Conference on Advancement in Computation and computer Technologies, InCACCT 2024

作者： Mehla, Anuj Deora, Sukhvinder Singh M.D.U Rohtak Department of Computer Science & Applications Rohtak India

ISBN: (纸本)9798350371314

India's economy heavily relies on agriculture, with over half of its land, which is 328.7 million hectares, designated as agricultural land. Agriculture generates around 17.8% of India's G.D.P. and over 18% of its exports in 2022-2023. More than half of India's workforce is employed in the agriculture industry. However, the success of agriculture in India is affected by several variables like soil quality, crop genetics, and climate. Precise yield prediction is necessary for creating import-export policies, increasing farmers' income, and for agri-commodity strategic action plans. It is also required for field-level quantification and financial evaluation. Yield prediction requires proficiency in climate change, water, pesticides, land area, weather factors, and soil characteristics. Recent studies have shown that machine learning algorithms driven by A.I. can predict wheat crop yields in India and other countries with promising results. This study compares various machine learning methods, such as Naïve Bayes (N.B.), K-Nearest Neighbor (K.N.N.), Gradient Boost (G.B.), Random Forest (R.F.), Decision Trees (D.T.), Extreme Gradient Boost (X.G.B.), and Artificial Neural Network (ANN) models. The results revealed that the best yield prediction models were the Random Forest (R.F.) and Extreme Gradient Boost (X.G.B.) models. © 2024 IEEE.

关键词： Crops

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：