检索结果-内蒙古大学图书馆

Expert Clouds and Applications (ICOECA), International Conference on

作者： Dheeraj Hebri S. Kirubakaran R. Rajitha Jasmine Anitha Poosamooper S. Rukmani Devi D Raja Joseph Department of Master of Computer Applications Srinivas Institute of Technology Valachil Mangalore Karnataka India Department of Computer Science Engineering CMR College of Engineering and Technology Hyderabad Telangana India Department of Information Technology R.M.K. Engineering College Kavaraipettai Thiruvallur Tamil Nadu India Department of Computer Applications Vel Tech Ranga Sanku Arts College Chennai Tamil Nadu India Department of Computer Science Saveetha College of Liberal Arts and Sciences SIMATS Deemed to be University Chennai Tamil Nadu India School of Aeronautical Sciences Hindustan Institute of Technology and Science Padur Chennai Tamil Nadu India

ISBN: (数字)9798350385793

ISBN: (纸本)9798350385809

Remote sensing is concerned with high-resolution geographical data. Its applications include farming, water resources, ecology, forests, deserts, marine applications, soil types, disaster alerts, and management. To extract the necessary information from satellite images, considerable image processing is required. Image segmentation and categorization into land cover categories is an important stage in satellite image processing. This article describes a method for categorizing and detecting different forms of land cover from satellite data. In this study, we examine satellite images for historical map classification using machine learning algorithms. We acquire Landsat images to complete this tedious task. The images are carefully labeled using the ArcMap software. We categorize areas into five types: forest, building, water, barren, and agricultural land. The images are then sent to the Convolutional Neural Network (CNN) Model for feature extraction. The retrieved features were then exposed to three Machine Learning (ML) models: Support Vector Machine (SVM), Naive Bayes (NB), and Decision Tree (DT). Standard classification measures are used to analyze the outcomes of all three models. When compared to the other two models in satellite image classification, CNN feature extraction with SVM classifier achieves the greatest accuracy of 95%.

关键词： Support vector machines Forests Machine learning algorithms Biological system modeling Disasters Land surface Landsat

来源：评论

学校读者我要写书评

暂无评论

Research on Majorization Algorithm and Application of Geotechnical Engineering Structure Based on Granule Swarm Majorization 2

Research on Majorization Algorithm and Application of Geotec...

引用

2nd International Conference on Smart Technologies for Smart Nation, SmartTechCon 2023

作者： Gnana Soundari, A. Al-Fatlawy, Mohammed Hussien Omkar, Jamvant Arun Balaji, N. Suseela, D. Asha, V. Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Tamil Nadu Chennai India College of Technical Engineering The Islamic University Najaf Iraq Department of Electronics & Communication IES College Of Technology MP Bhopal462044 India New Prince Shri Bhavani College of Engineering and Technology Tamil Nadu India Department of Artificial Intelligence and Machine Learning Bannari Amman Institute of Technology Tamil Nadu Sathyamangalam India Department of Master of Computer Applications New Horizon College of Engineering Bellandur Post Bengaluru560103 India

ISBN: (纸本)9798350305418

The traditional majorization design method makes too many restrictions on the objective function to be optimized and its constraints, which brings a lot of inconvenience to solving majorization problems in practical projects. A new stochastic Optimization algorithm based on swarm intelligence - granule swarm algorithm (PSO) was put forward in, and it has been widely concerned by researchers. When the algorithm is initialized, the granules are randomly divided into several sub-granule groups, each sub-granule group evolves independently according to a given strategy, and random migration and adaptive mutation of granules are carried out in the specified period of evolution to maintain the diversity of the entire population., to avoid premature convergence. The inverse analysis of geotechnical engineering majorization is essentially a typical majorization problem of complex nonlinear functions. The use of global majorization algorithm is an ideal way to solve this problem. low productivity. The new algorithm is applied to the elastic-plastic parameter inversion of geotechnical materials. The results show that compared with the conventional granule swarm majorization algorithm, the improved algorithm significantly improves the search efficiency of parameters, and the results that meet the accuracy requirements can be obtained with less iterations, which reduces the amount of calculation of elastic-plastic back analysis of geotechnical engineering. It is a feasible parameter inversion method. © 2023 IEEE.

关键词： Efficiency Geotechnical engineering Granule Swarm Particle swarm majorization Structural majorization

来源：评论

学校读者我要写书评

暂无评论

Crop Yield Prediction Using Deep Reinforcement Learning

Crop Yield Prediction Using Deep Reinforcement Learning

引用

Trends in Electrical, Electronics, computer Engineering Conference (TEECCON)

作者： Sudhakar Deivasigamani A Jaya Mabel Rani R Natchadalingam P Vijayakarthik G Bala Sendhil Kumar Pundru Chandra Shaker Reddy Scrum Master Digipulse Technologies Inc New Jersy USA Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India CSE-Data Science R.L.Jalappa Institute of Technology Bengaluru Karnataka India Computer Science and Engineering R.L.Jalappa Institute of Technology Bengaluru Karnataka India Master of Business Administration Sri Manakula Vinayagar Engineering College Puducherry India School of Computer Science and Engineering Lovely Professional University Phagwara Punjab India

Predicting crop production using information about the environment, soil, water, and crops themselves is an area ripe for investigation. Deep learning-based models often extract crop attributes for prediction. These techniques have the following drawbacks: The quality of the extracted characteristics substantially affects the efficacy of those models, and there is no simple non-linear or linear mapping between raw data and crop production estimates. Deep RL guides and inspires to compensate. Deep reinforcement learning uses RL and DL to accurately forecast agricultural yields from raw data. A Deep Recurrent Q-Network model predicts agricultural yield. This model uses Q-Learning reinforcement learning and a Recurrent Neural Network deep learning algorithm. Data parameters feed the Recurrent Neural network's layers. Q-learning networks forecast agricultural yields from data. Q-values are linear mappings from Recurrent Neural Network output values. A threshold and parametric features help the reinforcement learning agent predict crop productivity. Finally, the agent is awarded a final score that takes into account the steps taken to both reduce error and improve forecast accuracy. By maintaining the original data distribution, the suggested model efficiently predicts the crop production with an accuracy of 93.7%, exceeding competing models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advanced Hybrid Intelligence Framework for Scalable and Robust Big Data Analytics

Advanced Hybrid Intelligence Framework for Scalable and Robu...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： S P Sreeja D Sreenivasulu Alok Jain R. Akhilesh Reddy Fatimah Dhari Jabbar V. Keerthi Master of Computer Application New Horizon College of Engineering Bangalore India Computer Science and Engineering (Data Science) Institute of Aeronautical Engineering Dundigal Hyderabad India Lovely Professional University Phagwara India Department of CSE-AI&ML MLR Institute of Technology Hyderabad Telangana India Radiology Techniques Department College of Medical Technology The Islamic University Najaf Iraq Department of CSE GRIET Bachupally Hyderabad Telangana India

ISBN: (数字)9798350350067

ISBN: (纸本)9798350350074

The phenomena of data explosion in different areas of life require enhanced methods to performing big data analysis. This paper proposes the Hybrid Intelligent Machine Learning System (HIMLS) which work through the combination of multiple machine learning approaches to improve the efficacy of big data analysis. HIMLS applies the benefits of both supervised and unsupervised learning, integrates deep learning models and ensemble methods to solve the difficulties which are from high-dimension learning and heterogeneous data. As a result of combining feature selection with the process of dimensionality reduction HIMLS moderates the curse of dimensionality which enhances the models’ predictive capability while lowering the computational requirements. It is proved that the system works on actual big data implementation, exhibits a better solution in terms of the accuracy of the model, size, and stability aspects in contrast to the conventional machine learning approaches. This research also analyses the effects that different techniques of hyperparameters optimization select and the involvement of distributed computing systems for speeding up analytics. Thus the study infers HIMLS as a suitable solution to the shortcomings characterized by current big data analytical techniques, giving an efficient method for harnessing big data solutions.

关键词： Dimensionality reduction Accuracy Computational modeling Distributed databases Big Data Feature extraction Data models Stability analysis Ensemble learning Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Applying Deep Learning and Transfer Learning Techniques for Improving Animal Intrusion Detection in Agriculture Farms

Applying Deep Learning and Transfer Learning Techniques for ...

引用

Data science, Agents & Artificial Intelligence (ICDSAAI), International Conference on

作者： R. Saraswathi G. Shobarani A. Subramani D. Tamilarasan Department of Master of Computer Applications Sreenivasa Institute of Technology and Management Studies Chittoor Andhra Pradesh India Department of Artificial Intelligence Islamiah Women’s Arts and Science College Vaniyambadi Thiruppatur Tamil Nadu India Department of Computer Science M.V.Muthiah Government Arts College for Women Dindigul Tamilnadu India Department of Master of Computer Applications Sri Venkateswara College of Engineering and Technology Chittoor Andhra Pradesh India

Due to the nature of farmlands or provincial landscapes, monitoring is required to keep unauthorized persons out of the region and to safeguard the district from wildlife. Various techniques point straight towards perception, which is primarily for human gatecrashers, but we sometimes forget that the primary opponents of such farmers are the animals who trash the crops. Crop damage caused by monster attacks is one of the most serious dangers to collect yield. Crop striking is becoming one of the most distant human-natural life conflicts as created land expands into formerly untamed life domain. The principle is compelling and forceful checking of the wild creatures’ squarely at home. This research paper is focused to develop computational techniques for identifying the animals that swoop into the agricultural area. Because there are so many various kinds of organisms, genuinely recognizing them may be a difficult task. In this paper, we have used a camera to capture routine images of the surrounding area and to observe the entire homestead at regular intervals. With the aid of further developed learning models, we can distinguish between different stages of a creature’s development and play appropriate noises to frighten them off. The various convolutional brain network libraries and ideas that went into creating the model are acknowledged in this study. We have worked on the path of creature interruption discovery in agribusiness areas using deep learning and move learning techniques.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Smart Dome 4.0: Low-Cost, Independent, Automated Energy System for Agricultural Purposes enabled by Machine Learning 2

Smart Dome 4.0: Low-Cost, Independent, Automated Energy Syst...

引用

2021 2nd International Symposium on Automation, Information and Computing, ISAIC 2021

作者： Budiman, Arief S Gunawan, Fergyanto Djuana, Endang Pardamean, Bens Romeli, Sugiarto Putri, Dianing Nn Aji, Daisman Pb Rahardjo, Kuat Stevanus Ilham Wibowo, M. Daffa, Nadiev Owen, Raymond Industrial Engineering Department BINUS Graduate Program - Master of Industrial Engineering Bina Nusantara University Jakarta Indonesia Department of Manufacturing and Mechanical Engineering and Technology Oregon Institute of Technology Klamath FallsOR97601 United States Electrical Engineering Department Faculty of Industrial Technology Universitas Trisakti Jakarta Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia PT. Impack Pratama Industri Tbk Jakarta Indonesia Mechanical Engineering Department Faculty of Industrial Technology Universitas Trisakti Jakarta Indonesia Industrial Engineering Department Faculty of Engineering Bina Nusantara University Jakarta Indonesia

Many economically essential crops in Indonesia (such as coffee, tea, chocolate, or copra) require storage or drying under certain environmental conditions, especially temperature and humidity. The solar dryer dome, typically used for agricultural purposes in Indonesia, produces a sufficient amount of heat to increase the evaporation rate inside the dome and reduce the moisture content of the commodity. A hybrid solar dryer accompanied by a photovoltaic panel, fan, and ventilation system is generally suitable. The system can provide an optimum environment with minimum control. However, as the outdoor temperature and humidity change dramatically, such as at night time, more control is required. Based on Industry 4.0 technologies, we have developed a new kind of hybrid solar dryer that provides an optimum environment 24/7. The system, called Smart Dome 4.0, is an intelligent, low-cost, self-sufficient drying and storage system to support Indonesia Agriculture 4.0. The system has a local power generation unit to self-sustain the required energy and operate without connecting to the electricity grid. The system utilizes a machine-learning algorithm to predict the environmental condition and optimally uses self-generated electric power. The developed Smart Dome 4.0 technology is critical to producing a sustainable solar dome under drastic environmental dynamics. © Published under licence by IOP Publishing Ltd.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised classification of social media posts: Identifying sex-industry posts to enable better support for those experiencing sex-trafficking

arXiv

引用

arXiv 2021年

作者： Simonson, Ellie Louise Master of Engineering in Electrical Engineering Computer Science at The Massachusetts Institute of Technology

Social media is both helpful and harmful to the work against sex trafficking. On one hand, social workers carefully use social media to support individuals experiencing sex trafficking. On the other hand, traffickers use social media to groom and recruit individuals into trafficking situations. Additionally, individuals experiencing sex trafficking can use social media as a means to meet sales quotas set by the traffickers [1]. There is the opportunity to use social media data to better provide support for people experiencing trafficking. While Artificial Intelligence and Machine Learning have been used in work against sex trafficking, they predominantly focus on detecting Child Sexual Abuse Material. Work using social media data has not been done with the intention to provide community level support to individuals of all ages experiencing trafficking. Within this context, this thesis explores the use of semi-supervised classification to identify social media posts that are a part of the sex industry1. Instagram is one of several social media platforms used by individuals within the sex industry, and it was the primary source of data. Several methods were explored for machine learning. However, the primary method used was semi-supervised learning, which has the benefit of providing automated classification with a limited set of labelled data. For this method, social media posts were embedded into low-dimensional vectors using FastText and Doc2Vec models. The data were then clustered using Kmeans clustering, and Cross-Validation was used to determine label propagation accuracy. Copyright © 2021, The Authors. All rights reserved.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Development of an Electric Automation Control Model Using Artificial Intelligence

Development of an Electric Automation Control Model Using Ar...

引用

International Conference on Computational and Characterization Techniques in Engineering & sciences (CCTES)

作者： V. Srikanth P. Aswini V. Asha Khobragade Pithamber Rajeev Sobti Z. Salman School of Sciences and Computer Studies CMR University (SATELLITE CAMPUS-OMBR LAYOUT) Bengaluru India Computer Science and Engineering(Data Science) Institute of Aeronautical Engineering Hyderabad India Department of Master of Computer Application New Horizon College of Engineering Bangalore India Department of Electronics and Communication Engineering MLR Institute of Technology Hyderabad Telangana India Lovely Professional University Phagwara India Hilla University College Babylon Iraq

ISBN: (数字)9798350364699

ISBN: (纸本)9798350364705

The design of an AI-based electrical computerization control system is implemented to efficiently address the challenges encountered by contemporary electrical engineering. A model of an AI-based control system for electrical automation is presented. To achieve optimal control settings, the control strategy makes use of an artificial intelligence system. Even in the presence of a twenty per cent load intervention and 2.1 Hz wavelength interference, the research demonstrates that the organisation has significant anti-interference capabilities, as shown by an acceptable fail rate of 0.02 for each at the system management level. Consequently, using an AI algorithm in automated electrification control may lead to a significant improvement in control reaction time, cost savings, and efficient construction.

关键词： Industries Automation Costs Interference Electrification Control systems Time factors Artificial intelligence Turbines Load modeling

来源：评论

学校读者我要写书评

暂无评论

FogNet: Custom CNN with optimal feature selection-based combat model for secured fog computing environment

引用

e-Prime - Advances in Electrical Engineering, Electronics and Energy 2024年 8卷

作者： Sahu, Dipti Prava Tripathy, Biswajit Samantaray, Leena Biju Patnaik University of Technology Department of Computer Science and Engineering Odisha Rourkela 769004 India Einstein College of Computer Application and Management Master of Computer Applications Odisha Khurda 752060 India Ajay Binay Institute of Technology Department of Electronics and Communication Engineering Odisha Cuttack 753014 India

In recent years, the increasing number of connected devices and the exponential growth of data generated by these devices have posed significant challenges for intrusion detection systems (IDS) in fog computing environments. However, conventional IDS failed to provide better attack detection performance in fog computing networks. So, this work proposes a custom convolutional neural network (CCNN) with optimal feature selection-based combat model for secured fog computing environment. Initially, preprocessing of the dataset aims to enhance the quality of the input data by removing attack labels, reducing dimensionality, and extracting relevant features. Then, comprehensive learning particle swarm-based effective seeker optimization (CLPS-ESO) is employed to extract features by leveraging a comprehensive learning strategy and the powerful optimization capabilities of effective seeker particle swarm optimization. To further enhance the feature selection performance, the random forest-dependent African buffalo optimization with weighted genetic algorithm, here after referred as RF-IABO-WGA, is utilized to identify the most discriminative features from the CLPS-ESO dataset. By selecting a subset of informative features, the computational complexity is reduced, and the detection accuracy is improved. Finally, the selected features are fed into a custom convolutional neural network (CCNN) classifier, which leverages the power of deep learning to accurately classify network traffic as either normal or malicious. The CCNN architecture can effectively learn complex patterns and capture the underlying characteristics of network data, enabling accurate intrusion detection in fog computing environments. Experimental results on a UNSW-NB dataset demonstrate that the proposed FogNet resulted in accuracy of 99.771878 %, precision of 99.770460 %, recall of 99.538589 %, and F1-score of 99.653512 %, which are superior performances compared to existing approaches. © 2024 The Author(s)

关键词： African buffalo optimization Effective seeker optimization Feature analysis Fog computing Intrusion detection system Malicious activity detection Resource utilization

来源：评论

学校读者我要写书评

暂无评论

Utilizing Random Forests for High-Accuracy Classification in Medical Diagnostics

Utilizing Random Forests for High-Accuracy Classification in...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Meenakshi Maindola Ramy Riad Al-Fatlawy Rakesh Kumar Nandini Shirish Boob S P Sreeja N Sirisha Abhinav Srivastava Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Department of computers Techniques engineering College of technical engineering The Islamic university Najaf Iraq Department of Computer Engineering & Applications GLA University Mathura Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamilnadu Master of Computer Application New Horizon College of Engineering Bangalore Department of Computer Science and Engineering MLR Institute of Technology Hyderabad Telangana FS University Shikohabad Firozabad India

ISBN: (数字)9798350350067

ISBN: (纸本)9798350350074

In recent years, medical diagnostics has increasingly relied on machine learning techniques to improve accuracy and efficiency. Among these, the Random Forest algorithm has emerged as a powerful tool for classification tasks due to its robustness and ability to handle complex datasets. This paper explores the application of Random Forests in medical diagnostics, specifically focusing on enhancing the accuracy of disease classification. By analyzing large, heterogeneous medical datasets, we demonstrate how Random Forests can outperform traditional classification algorithms, offering high precision in identifying and classifying diseases. Key features, such as decision tree ensemble methods and bootstrap aggregation, are utilized to minimize overfitting and improve model generalization. The research compares Random Forests to other machine learning models, such as Neural Networks and Support Vector Machines, and finds that Random Forests perform better in terms of dependability and classification accuracy. We further emphasise that the technique can scale to big datasets and that it can manage missing data. The findings show that Random Forests might be a useful tool for accurate and early diagnosis when incorporated into clinical procedures. The findings of this study highlight the promise of machine learning, and Random Forests in particular, to revolutionise healthcare diagnostics and enhance patient results.

关键词： Radio frequency Support vector machines Accuracy Scalability Robustness Classification algorithms Medical diagnosis Random forests Medical diagnostic imaging Diseases

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：