检索结果-内蒙古大学图书馆

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Bhadula, Shuchi Adnan, Myasar Mundher Kumar, Rakesh Rana, Ajay Kaliyaperumal, Gopal Rao, Bolleddu Devananda Boob, Nandini Shirish Graphic Era Deemed to be University Department of Computer Science & Engineering Dehradun India The Islamic university College of technical engineering Department of computers Techniques engineering Najaf Iraq Gla University Department of Computer Engineering & Applications Mathura India Amity University Uttar Pradesh Greater Noida India New Horizon College of Engineering Department of Mechanical Engineering Bangalore India Mlr Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350350067

The exponential growth of data in recent years has necessitated the development of more efficient and scalable machine learning algorithms to handle large-scale data analysis. Random Forest (RF) algorithms, known for their robustness and accuracy, find extensive use in the realms of classification and regression. However, their performance can be significantly hindered when dealing with massive datasets due to increased computational complexity and resource demands. This paper presents a comprehensive approach to optimizing Random Forest algorithms for large-scale data analysis. We explore various strategies, including data partitioning, algorithmic changes and parallel processing to make RF algorithms more efficient and scalable. Additionally, we introduce novel techniques for feature selection and hyperparameter tuning to improve model performance. Extensive experiments conducted on multiple large-scale datasets demonstrate the effectiveness of the proposed optimizations in reducing computation time and memory usage while maintaining or even enhancing predictive accuracy. From genomics to finance, the optimised Random Forest method shows promise as a robust tool for large-scale data processing in many applications, according to the findings. © 2024 IEEE.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

Enhanced ML Based Content-Based Image Retrieval for Mobile Devices

Enhanced ML Based Content-Based Image Retrieval for Mobile D...

引用

Artificial Intelligence and Emerging technology (Global AI Summit), International Conference on

作者： Km Meenakshi Kirti Dilip Singh Priya Batta Rakhi Chauhan Deepshikha Bhargava Bhanu Prakash Lohani Amity School of Engineering & Technology Amity University Greater Noida Department of Computer Science & Engineering Chandigarh University Mohali India Department of Computer Science & Engineering Geeta University Panipat Haryana

ISBN: (数字)9798350379716

ISBN: (纸本)9798350379723

Image retrieval systems based on content can be developed for mobile applications that provide users with a seamless and efficient way to search for images based on their content. The development of CBIR systems for mobile applications presents unique challenges and opportunities. Mobile devices typically have limited computational resources, storage capacity, and network bandwidth compared to traditional computing platforms. Therefore, CBIR systems designed for mobile applications must be lightweight, efficient, and optimized to run smoothly on these devices. The Adaboost algorithm progressively learns weak classifiers and aggregates them to construct a robust final classifier. Subsequently, a weak learner is introduced, and the data undergoes reweighting. Misclassified test images are assigned greater importance while correctly classified ones are downweighted. Consequently, subsequent weak learners prioritize the query images previously misclassified by their predecessors. The average precision is increased in further iterations to 95.6% from the initial iteration of 94.9%. Average recall shows a little more improvement from the previous set by increasing from round 1 with 94.1%, and increasing to 95.9% towards the last round of iteration. The F-Measure keeps fairly stabilized at 95.1478 after the first round. The time taken by every iteration reduces slightly from 3.

关键词： Aggregates Image retrieval Bandwidth Mobile handsets Mobile applications Classification algorithms Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Glaucoma Classification using Light Vision Transformer

引用

EAI Endorsed Transactions on Pervasive Health and technology 2023年 9卷

作者： Singh, Piyush Bhushan Singh, Pawan Dev, Harsh Tiwari, Anil Batra, Devanshu Chaurasia, Brijesh Kumar Department of Computer Science and Engineering Amity School of Engineering and Technology Lucknow Amity University Uttar Pradesh India Department of Computer Science and Engineering Pranveer Singh Institute of Technology Kanpur India Amity School of Engineering and Technology Lucknow Amity University Uttar Pradesh India Department of Information Technology Pranveer Singh Institute of Technology Kanpur India

INTRODUCTION: Nowadays one of the primary causes of permanent blindness is glaucoma. Due to the trade-offs, it makes in terms of portability, size, and cost, fundus imaging is the most widely used glaucoma screening technique. OBJECTIVES:To boost accuracy,focusing on less execution time, and less resources consumption, we have proposed a vision transformer-based model with data pre-processing techniques which fix classification problems. METHODS: Convolution is a "local" technique used by CNNs that is restricted to a limited area around an image. Self-attention, used by Vision Transformers, is a "global" action since it gathers data from the whole image. This makes it possible for the ViT to successfully collect far-off semantic relevance in an image. Several optimizers, including Adamax, SGD, RMSprop, Adadelta, Adafactor, Nadam, and Adagrad, were studied in this paper. We have trained and tested the Vision Transformer model on the IEEE Fundus image dataset having 1750 Healthy and Glaucoma images. Additionally, the dataset was preprocessed using image resizing, auto-rotation, and auto-adjust contrast by adaptive equalization. RESULTS: Results also show that the Nadam Optimizer increased accuracy up to 97% in adaptive equalized preprocessing dataset followed by auto rotate and image resizing operations. CONCLUSION: The experimental findings shows that transformer based classification spurred a revolution in computer vision with reduced time in training and classification. © 2023 Singh et al.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

MRI Based Health Detection Using Machine Learning Techniques

MRI Based Health Detection Using Machine Learning Techniques

引用

International Conference on Confluence The Next Generation Information technology Summit (Confluence)

作者： Rishab Ranjai Sumita Gupta Department of Computer Science & Engineering Amity School of Engineering and Technology Amity University Uttar Pradesh Noida U.P. India

Health has a significant influence on one's wellbeing and quality of life. By assisting medical practitioners, suggesting possible therapies, and allowing early illness identification, machine learning techniques have the potential to completely transform the healthcare sector. This research assesses many machine learning approaches, such as Decision Tree classifier, Random Forest classifier, Logistic Regression, and Support Vector Machine, for identifying heart health concerns. It also offers a Convolutional Neural Network (CNN) model for brain tumor diagnosis. CNNs may detect tiny anomalies that may escape human inspection because of their expertise in processing medical pictures, such as MRI scans. The suggested 11-layer CNN model for cancer diagnosis has a 97.7% accuracy rate, a 96.9% recall rate, and a 1.36% false positive rate. Furthermore, by evaluating large amounts of patient data to pinpoint those who are at risk, machine learning algorithms also significantly contribute to the prediction of cardiac disease.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lip Reading Into Text Using Deep Learning

Lip Reading Into Text Using Deep Learning

引用

International Conference on Confluence The Next Generation Information technology Summit (Confluence)

作者： Krishna Manglani Utkarsh Bahuguna Subhash Chand Gupta dept. of Computer Science Amity School Of Engineering and Technology Uttar Pradesh India

An essential part of computer vision, lip reading, has grown significantly and is now used in autonomous driving, public safety, and hearing-impaired communication. This work provides an in-depth analysis of both conventional and deep learning-based lip reading systems, examining their development over time, difficulties encountered, and critical role in human communication. The suggested LipNet model, which leverages the complementary abilities of Long Short-Term Memory networks (LSTMs) for temporal modelling and Convolutional Neural Networks (CNNs) for spatial feature extraction, is a central focus of this research. When LipNet is tested using the GRID Corpus dataset, it outperforms baseline models in terms of performance. Saliency maps and viseme analysis highlight LipNet's ability to capture phonologically relevant areas in lip motions, providing insight into the network's attention processes. Apart from examining the importance of datasets such as OuluVs2and GRID Corpus, this study presents GhostNet, a lightweight model that tackles the requirement for effective network designs. The testing results highlight LipNet's competitive Character Error Rate (CER) and Word Error Rate (WER) in comparison to baseline models, proving that it is the best method for real-world use. The research ends with a summary of potential future developments in lip reading technology, such as modal integration, realtime applications, personalisation, ethical issues, and the goal of creating a communication environment that is more inclusive. This study highlights the effectiveness of LipNet and paves the way for future developments in the ever-evolving area of lip reading by examining a variety of methodologies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cloud Computing and Comparison based on Service and Performance between Amazon AWS, Microsoft Azure, and Google Cloud

Cloud Computing and Comparison based on Service and Performa...

引用

2021 International Conference on Technological Advancements and Innovations, ICTAI 2021

作者： Kaushik, Prakarsh Rao, Ashwin Murali Singh, Devang Pratap Vashisht, Swati Gupta, Shubhi Computer Science and Engineering Amity School of Engineering and Technology Greater Noida India Amity School of Engineering and Technology Department of Computer Science Greater Noida India

ISBN: (纸本)9781665420877

Cloud computing is the on-request supply of computing resources through the Web with pay-as-you-use billing. Instead of purchasing, operating, and maintaining physical computers, hardware, and servers, cloud solutions providers such as Microsoft Azure of Microsoft, Amazon Web Services (AWS) of Amazon, and Google Cloud Platform (GCP) by Google offer cloud solutions such as processing power, memory, and databases on an as-needed basis. This research paper discusses the architecture and types of cloud computing services, as well as comparison of the performance and service among three main Cloud Computing platforms: Microsoft Azure, Amazon AWS, and Google Cloud Platform. All three systems have been evaluated in identical virtual environments, specifically micro instance of Ubuntu 16.04. The benchmark application Phoronix Test Suite 10.4 is used to assess performance, and the results for the Apache, Dbench, and RAM speed benchmarks are evaluated in this paper. © 2021 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Comprehensive asset surveillance and prediction modeling using real time data analytics

Comprehensive asset surveillance and prediction modeling usi...

引用

Computational Intelligence, Communication technology and Networking (CICTN), International Conference on

作者： Aayushi Rawat Sumita Gupta Gauri Raghuvanshi Tanya Aggarwal Vinayak Majhi Department of Computer Science and Engineering Amity School of Engineering and Technology Amity University Noida Uttar Pradesh India Amity Innovation and Design Center Amity University Noida Uttar Pradesh India

ISBN: (数字)9798331530389

ISBN: (纸本)9798331530396

The rapid evolution in the technology industry highlights the importance of developing a more advanced asset tracking system. The need for efficient and accurate asset management has become crucial and predominant across various industries. This paper displays the utilization of low-cost, and energy efficient technologies like Seeed Studio XIAO nRF52840 and Arduino Uno in designing and implementation of an asset tracking system. The design of the system primarily focuses on providing real time location of an asset, improving its tracking accuracy and operational efficiency. This study practically demonstrates the use of inexpensive microcontroller platforms along with BLE technology so as to develop an asset tracking system, the scalable solution that can be implemented across various industries such as logistics, healthcare, and manufacturing.

关键词： Industries Accuracy Microcontrollers Surveillance Medical services Predictive models Real-time systems Manufacturing Internet of Things Logistics

来源：评论

学校读者我要写书评

暂无评论

A comparative analysis of different cloud computing method for scheduling healthcare tasks

A comparative analysis of different cloud computing method f...

引用

Signal Processing and Advance Research in Computing (SPARC), International Conference on

作者： Pallab Banerjee Shavi Snehal Sonam Kumari Biresh Kumar Kanika Thakur Manorama Patnaik Computer Science Engineering Amity University Ranchi Jharkhand India Amity School of Information Technology Amity University Ranchi Jharkhand India Computer Science and Engineering Galgotia University Greater Noida campus

ISBN: (数字)9798350385205

ISBN: (纸本)9798350385212

The problem of efficient task scheduling in cloud-integrated, Internet of Things-based healthcare monitoring systems is examined in this work. We suggest Prioritized Sorted Task-Based Allocation (PSTBA), a novel scheduling method, to enhance task execution and boost system performance. In order to guarantee that vital healthcare monitoring tasks are finished on time, PSTBA ranks jobs according to their criticality, expected processing time (EPT), and virtual machine wait time. The process entails putting PSTBA into practice in an IoT cloud context and assessing its effectiveness using in-depth CloudSim simulations. The findings show that PSTBA works noticeably better than the current techniques, such as First-Come, First-Served (FCFS) and Sorted Task-Based Allocation (STBA) PSTBA specifically lowers the failure rate by 20% and 35.6%, raises the guarantee ratio by 2.5% and 4.8%, and decreases latency by 12.6% compared to STBA and 79.2% compared to FCFS. Moreover, PSTBA successfully reduces the number of key activities missed by 14.9% when compared to STBA and 51% when compared to FCFS. To sum up, PSTBA is a very successful scheduling method that improves job prioritizing and system stability for IoT-based healthcare systems.

关键词： Cloud computing Visualization Processor scheduling Medical services Quality of service Virtual machines Workstations Resource management Time factors Monitoring

来源：评论

学校读者我要写书评

暂无评论

FedHZone: Federated Learning Based Hazardous Zone Detection Using Internet of Drone Things

FedHZone: Federated Learning Based Hazardous Zone Detection ...

引用

2024 IEEE International Conference on Communications, Computing, Cybersecurity and Informatics, CCCI 2024

作者： Biswas, Payel De, Debashis Obaidat, Mohammad S. Hazra, Arnab Sadoun, Balqies Jogesh Chandra Chaudhuri College Department of Computer Science Kolkata India Maulana Abul Kalam Azad University of Technology Centre of Mobile Cloud Computing Department of Computer Science and Engineering West Bengal WB Nadia India School of Computer and Communication Engineering University of Science and Technology Beijing Beijing100083 China School of Computing SRM University Department of Computational Intelligence SRM Nagar TN Kattankulathur603203 India School of Engineering The Amity University UP Noida201301 India Dr. Sudhir Chandra sur Institute of Technology & Sports Complex Department of Computer Science and Engineering Kolkata India College of Engineering Al Balqa ' Applied University Al-Salt19117 Jordan

ISBN: (纸本)9798350349832

Air pollution can affect human health, so it is necessary to predict the air quality index (AQI) in advance. In this work, air quality data collected by the Internet of Drone Things (IoDT) is predicted and analyzed to detect highly polluted zones using a distributed privacy-preserving federated learning (FL) approach. Air quality data for a particular zone is collected and then fed into a Long short-Term memory (LSTM) based model to predict the pollution level in local training. Global aggregation is done by an IoDT-mounted central server to aggregate the received models from the local IoDT level. Privacy-preserving FedHZone predicts and analyses the AQI values from the past time series dataset in a multi-drone environment. This work detects the most hazardous zone in a larger region of Jaipur, Rajasthan using real-Time data. The result shows FedHZone with stacked LSTM having ''2%-7% better accuracy than the vanilla LSTM-based model. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Cohort study on recognition of plant species using Deep Learning methods

Cohort study on recognition of plant species using Deep Lear...

引用

2022 International Conference on Applications of Intelligent Computing in engineering and science, AICES 2022

作者： Barhate, Deepti Pathak, Sunil Dubey, Ashutosh Kumar Nemade, Varsha Amity School of Engineering & Technology Department of Computer Science & Engineering Amity University Rajasthan Jaipur India Chitkara University School of Engineering and Technology Chitkara University Himachal Pradesh India SVKM's NMIMS MPSTME Maharashtra Shirpur India

Plants play a vital role in each living organism's life since it maintains the environment and provides us valuable medicine, food, fragrance etc. Knowledge of species is important for the protection of biodiversity. The identification of species of plants by a manual method by botanist is tedious work besides the complex botanical terms used by an expert are annoying for a non-expert. This may lead to the obstruction for learners interested in procuring knowledge of plant species. By applying the classification of species one can also capture crops from weed for automated weedicide. Species of plant recognition are a matter of huge significance in various areas of farming, maintenance of environmental, natural, manufactured goods and medicine invention, and other related areas. Leaf color leaves contour, shape, leaf size, flowers, texture, margins, etc. are the features of plants which can be used for classification, and however, extraction of traits from selected features is the most important status in the classification. In this paper, a review-based study is done which is based on approaches such as Machine learning algorithm, Deep Learning, Convolutional Neural Networks (CNN), etc. are compared. Various classification methods like K-nearest neighbor (KNN), Naïve baise(NB), Random forest are also studied. Mostly used datasets such as Flavia, swedish, Leafsnap, ICL with their species wise features were studied. © Published under licence by IOP Publishing Ltd.

关键词： Decision trees

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：