检索结果-内蒙古大学图书馆

35th IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2024

作者： Karppinen, Pasi Bandaranayake, Sameera Haukipuro, Lotta Elmistikawy, Yomn Saarnisaari, Harri University of Oulu Faculty of Information Technology and Electrical Engineering Oulu Finland University of Oulu Faculty of Science Oulu Finland Luleå University of Technology Electrical and Space Engineering Department of Computer Science Luleå Sweden

ISBN: (纸本)9798350362244

Well-working Internet connectivity is a fundamental citizen right and a necessity in modern digital societies. Nevertheless, the digital divide persists and often affects rural or remote areas. To bridge the digital divide, we need to understand the specific rural use cases and challenges. This would increase understanding about problems weak Internet connectivity causes, what is required from the connectivity technology and what is needed from policymakers and regulation. The goal of this paper is to identify rural use cases and analyze consequences to future connectivity technology through a mixed-methods approach: we investigated the divide and its consequences by a questionnaire and interviews conducted in northern Europe. The study found that the main issues faced by rural internet users are related to capacity, availability, and vulnerability of internet services. These issues hinder their daily life, work activities, and expose them to system-level risks. The article discusses how these findings can inform the development of more inclusive and resilient internet connectivity solutions. © 2024 IEEE.

关键词： digital divide mobile communication rural connectivity social sustainability

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Sentiment Analysis: Exploring the Power of Deep Learning Techniques in Opinion Mining

Deep Learning for Sentiment Analysis: Exploring the Power of...

引用

2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023

作者： Sindhu, L. Rameshkumar, M. Kumar, Gotte Ranjith Manjunath, B.N. Sapna Kumari, C. Sona College of Technology Department of Information Technology Salem India Paavai Engineering College Department of Computer Science and Engineering India Sr University School of Computer Science & Artificial Intelligence Warangal India R.L. Jalappa Institute of Technology Department of Computer Science & Amp Engineering Bangalore India Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Bengaluru India

ISBN: (纸本)9798350313413

Sentiment analysis (SA) is a popular method for collecting relevant and arbitrary information from text-based data. To locate, examine, extract reactions, and emotions from the data or states, it applies computational linguistics, biometrics, text analysis, and Natural Language Processing (NLP). A SA model can be developed and improved with the use of the features analysis method. However, it can be difficult to find the best classification methods for this type of data. When compared to current feature-based methods, deep learning models for the analysis of sentiment, are capable of providing precise representation and improved performance. In this paper, the deep learning method was proposed for improving sentiment classification performance with a sophisticated embedding word method and develop a network of Convolutional Neural Network and Long short-term memory (CNN-LSTM). For the purpose of predicting the sentiment of tweets for classification, a large amount of Amazon data is analysed. This study, concentrate on improving sentiment analysis performance by building a CNN-LSTM network and particularized model of deep learning with novel word embedding techniques. The CNN-LSTM model has achieved 98.20% accuracy, 99.86% precision, 99.50% recall, and 98.78% recall in sentiment analysis. © 2023 IEEE.

关键词： Convolutional Neural Network Deep Learning Long-short-term memory (LSTM) Sentiment analysis Word embedding

来源：评论

学校读者我要写书评

暂无评论

IoT-Enabled Health Monitoring System for Safeguarding Vital Organs with Cloud-Based Diagnosis and Advanced Algorithms 4

IoT-Enabled Health Monitoring System for Safeguarding Vital ...

引用

4th IEEE International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2024

作者： Ahmad, Salman Khursheed Ikra, K.M. Sharma, Preeti Kaushik, Yogita Choudhary, Amar Tripathi, Pradeep Kumar Gl Bajaj Institute of Technology and Management Department of Applied Computational Science and Engineering Greater Noida India Mangalmay Institute of Engineering and Technology Department of Computer Science and Engineering Greater Noida India Raj Kumar Goel Institute of Technology Department of Computer Science -DS Ghaziabad India Sunder Deep Group of Institutions Department Mca Ghaziabad India Alliance University Department of Electronics and Communication Engineering Bengaluru India Ajay Kumar Garg Engineering College Department of Information Technology Ghaziabad India

ISBN: (纸本)9798350360165

This study presents a novel IoT-enabled fitness tracking device intended to improve patient care through the capture of real-time physiological records and predictive analytics. The system uses a variety of sensors, including an Arduino UNO, an LM35, a MAX30100 pulse charge and SPo2 sensor, and a stress sensor, to continuously gather health data from ten different patients. Proactive health assessments and early intervention are made possible by the combination of cloud-based analysis and advanced system learning models, such as Support Vector Machines (SVM), Artificial Neural Networks (ANN), K-Nearest Neighbours (KNN), and Recurrent Neural Networks (RNN). Tested on real-world datasets, the experimental results show how effective the device is at making accurate and timely predictions. Notably, SVM is the most accurate variant, closely followed by ANN, KNN, and RNN. The confusion matrices ensure accurate and thorough examination of each version's performance, aiding in selecting the most relevant set of rules for real-time health monitoring to be used by clinicians. The present study, as groundbreaking work, demonstrates a major leap in merging IoT with device expertise in the healthcare sector that usages new possibilities in proactive and personalized treatment strategies. The recommended tool's innovative and reliable predictive analytics can potentially revolutionize patient transportation in the healthcare system. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

An Efficient Selective Features Approach to Detect Hypothyroid Using Machine Learning 5th

An Efficient Selective Features Approach to Detect Hypothyro...

引用

5th International Conference on computer and Communication Technologies, IC3T 2023

作者： Chandra, N. Subhash Dhanikonda, Srinivasa Rao Jagli, Dhanamma Siddhartha, Nalla Department of Computer Science and Engineering CVR College of Engineering Hyderabad India Department of Information Technology BVRIT HYDERABAD College of Engineering for Women Hyderabad India V.E.S.Institute of Technology University of Mumbai Mumbai India Indian Institute of Technology Tirupati Tirupati India

ISBN: (纸本)9789819997039

The thyroid gland is a hormone-producing gland located in the upper part of the neck. It helps to regulate the metabolism of the body. Its malfunction might lead to either inadequate or excessive thyroid hormone production. Thyroid issues are classified as hyperthyroidism or hypothyroidism. Predicting thyroid illness is now more crucial than ever. Machine learning algorithms and data mining techniques are critical for dealing with today’s massive amounts of data and information, particularly in the health-care system. A specific dataset is created that contains patient-related medical data. Based on the attributes considered, it is possible to categorize thyroid disease into three categories: primary hypothyroid, compensated hypothyroid, and routine. To identify earlier, various conventional machine learning methods are utilized, including Random Forest, Decision Tree, and Artificial Neural Network (ANN). These algorithms carry out the classification and determine the status but fall short of the desired results, particularly in the medical sector. In order to accomplish the goal, this research developed an effective classification strategy to improve the performance of hypothyroid prediction and it is divided into two stages: data preprocessing and classification methods. During the preparation phase, the dataset was preprocessed using two methods: PCA and an Extra Tree classifier, and the data was enriched with the Synthetic Minority Oversampling Technique (SMOTE). The proposed approach's outcomes were compared to traditional methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach of Machine Learning Application in Astrophysics: Morphological Feature Wrapping Based Ensemble Method for Galaxy Shape Classification Using GAMA Dataset 1

引用

International Conference on Advances in Communication technology and computer engineering, ICACTCE 2023

作者： Sinha, Anurag Shahid, Mohammad Nandan, Amritesh Iwendi, Celestine Giri, Abhijeet Kumar Anand, Saprit Department of Computer Science and Information Technology IGNOU New Delhi India Department of Computer Science and Information Technology Amity University Jharkhand Ranchi India Department of Computer Science and Information Technology Graphic Era Deemed to be University Dehradun India School of Creative Technologies University of Bolton BoltonBL3 5AB United Kingdom Department of Computer Science and Engineering KIIT Bhubaneswar India

ISBN: (数字)9783031371646

ISBN: (纸本)9783031371639

The numerous strategies for the automated morphological categorization of galaxies, which uses a variety of supervised machine learning techniques, have not been well examined or compared. As the majority of star galaxy classifiers in use today use condensed summary data from catalogues, rigorous feature extraction and selection are required. With the aid of Deep Convolutional Neural Networks (CNN), a development in machine learning, it may automate the process of feature detection from data by a computer, therefore lowering the demand for qualified human input. Low-level artificial classification has made great progress. While this is the case, Deep Learning consistently outperforms traditional computers. analyzing large datasets while learning. We examine three machine learning techniques for categorizing morphological galaxies: Support Vector Machines (SVM), Random Forests (RF), and Naive Bayes (NB). We examine the efficacy of several machine learning algorithms on each feature representation of a galaxy using a collection of morphological features produced by image analysis as well as the raw image pixel data compressed using PCA (Principal Component Analysis) into PCA features. According to our experiments, RF outperformed SVM and NB. The remainder of the time, morphological features outperformed our PCA features in performance. Thus, the current mechanism is not extremely scalable. A probabilistic classifier that can scale, is based on source data, and requires the least amount of human interaction is essential to resolving these problems. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Exploring the Use of Long Short-Term Memory for Time Series Analysis

Exploring the Use of Long Short-Term Memory for Time Series ...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Sharma, Amit Kumar Neetha, S.S. Awasthi, Aishwary College of Engineering Teetthanker Mahaveer University Uttar Pradesh Moradabad India Department of Computer Science and Information Technology Bangalore India Sanskriti University Department of Mechanical Engineering Uttar Pradesh Mathura India

ISBN: (纸本)9798350383348

This abstract explores the applications of long short-time period reminiscence (LSTM) for time collection evaluation. Time series analysis is essential in many fields to explore past activities and predict future trends. LSTM networks are artificial neural networks that approach records in temporal order. They can gain knowledge of lengthy-time period dependencies and may be used for sequence prediction and forecasting obligations. This abstract discusses how LSTM networks can be carried out for time series evaluation, the benefits and challenges of such networks, and potential programs for using such networks for time series evaluation. The abstract concludes with a quick outline of continuing research in this area. This paper examines the usage of long short-time period reminiscence (LSTM) for time collection analysis. We examine using LSTMs for time collection evaluation and how they may be used to become aware of and distinguish between developments and styles in time series datasets. We gift a top-level view of LSTM architectures and discuss the effectiveness of their use of them for time collection analysis. We additionally speak about the ability of programs using LSTMs for time series analysis, including predicting stock market movement and personal conduct. ultimately, we talk about the demanding situations that want to be addressed to make LSTM fashions extra effective for time series analysis.. © 2024 IEEE.

关键词： conduct developments fashions personal programs

来源：评论

学校读者我要写书评

暂无评论

The Deep Learning and Machine Learning Methods for Botnet Identification in the Internet of Things 6

The Deep Learning and Machine Learning Methods for Botnet Id...

引用

6th International Conference on Contemporary Computing and Informatics, IC3I 2023

作者： Gangone, Anjali Bala, Bhoomeshwar Gangone, Swapna Bharat Kumar, G.J. CMR Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India Debre Tabor University Department of Information Technology Debre Tabor Ethiopia Mettu University Department of Computer Science Mettu Ethiopia

ISBN: (纸本)9798350304480

In recent years, IoT (Internet of Things) devices and their attendant solutions have become more prevalent, particularly in manufacturing, supply chain management, healthcare, transportation, and numerous other 'smart'settings. Thanks to IP (Internet Protocol) addresses designated to IoT devices, cyber-physical systems are now able to communicate with one another automatically. Inadequate protection on these ultimate platforms has resulted in attacks such as denial-of-service, Botnets, identity theft, and information theft. Mirai, Torii, Emotet, Dridex, Trickbot, Gluteba, and QBots are examples of Internet of Things-related threats. With the aid of AI, we can at last create cyber-physical systems that are both trustworthy and secure. Machine learning and deep learning approaches combat cyberattacks by identifying and blocking Botnets. This paper investigates Botnet attacks, which are prevalent in IoT devices due to a lack of security requirements during manufacturing or a lack of user security awareness. Anomaly detection is a potential weapon in the hands of machine learning or Deep Learning for identifying and preventing cyberattacks on Internet of Things devices. In this study, we present a Botnet detection system capable of detecting an attack on live traffic. Next, we employ the Aposemat IoT-23 dataset to evaluate and compare a variety of machine learning as well as deep learning techniques for detecting Botnets based on their conventional characteristics. Gated Recurrent Unit (GRU) is a deep learning model with a detection accuracy of 99.87% for identifying Botnets. Thirdly, we use the Wireshark program to investigate the Aposemat IoT- 23 dataset's raw packet captured (pcap) files for attacks. Then, we employ GRU, a deep learning model, to identify malware infections with a 99.89% success rate and reduced time complexities. © 2023 IEEE.

关键词： Botnet Cyberattack Deep Leaning Devices IoT Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Unlocking Complex Patterns Through the Power of Deep Learning for Advanced Data Analysis and Prediction

Unlocking Complex Patterns Through the Power of Deep Learnin...

引用

2024 International Conference on Cybernation and Computation, CYBERCOM 2024

作者： Sasikumar, S. Kumar, M. Guru Vimal Paramesh, J. Sriram, K.P. Anbalagan, E. Saveetha Engineering College Department of Computer Science and Engineering Chennai India Vel Tech Rangarajan Dr. Sagunthala R and D Institute of Science and Technology Department of Computer Science and Engineering Avadi Chennai600062 India St. Joseph's Institute of Technology Information Technology OMR Chennai600119 India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331542344

Supervised deep learning has brought changes to data analysis and prediction function by leveraging its capacity to make many number of relationships with heterogeneous forms of data. This paper compares deep learning techniques like Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Long Short-Term Memory (LSTM) networks in three tasks: There are three types of tasks, including image classification, time-series prediction, and text classification. In the picture simulation of the CIFAR-10 set for training, the accuracy of the ResNet model was 95% while the accuracy of VGG16 w 93%. When applied to the M4 competition dataset in time-series prediction, the LSTM model was superior to other benchmarks with MAE of 0.40 and RMSE of 0.60, with the RNN model giving MAE of 0.50 and RMSE of 0.65. It is 0.92 of accuracy, 0.91 of F1 score, and 0.921 for precision using the IMDB reviews dataset in text classification of movies using the CNN-LSTM hybrid model while the Bi-LSTM only had an accuracy of 0.89 and an F1 score of 0.889. Even though models, such as ResNet and Bi-LSTM, took slightly more time to train-Approximately 5.0 hours-it was because the epoch models were significantly superior to the baseline model. The present work focuses on the benefits of deep learning architectures in providing interpretable patterns in numerous applications. © 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

A GPU scheme for multi-secret visual sharing with varied secret dimensions and contrast enhancement using blind super-resolution

引用

International Journal of information technology (Singapore) 2024年第3期16卷 1801-1814页

作者： Holla, M. Raviraja Suma, D. Department of Information and Communication Technology Manipal Institute of Technology Manipal Academy of Higher Education (MAHE) Karnataka Manipal 576104 India Department of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education (MAHE) Karnataka Manipal 576104 India

Multi-secret visual sharing schemes are essential for secure and efficient sharing of sensitive visual information. However, existing schemes often overlook important considerations such as varied secret dimensions, contrast enhancement, and computational efficiency. This research addresses these challenges by proposing a comprehensive approach that addresses these limitations. Firstly, the scheme takes into account the varied dimensions of secret images encountered in real-world scenarios, allowing flexibility in sharing and reconstructing images of different sizes and aspect ratios. Secondly, the research integrates contrast enhancement techniques, such as blind super-resolution, to improve the visual quality and visibility of shared secret images affected by factors like noise, compression, or low lighting conditions. Lastly, to enhance the computational efficiency, the scheme leverages the power of Graphics Processing Units (GPUs) for parallel computing, enabling faster processing of large-scale image operations. The proposed scheme achieves outstanding results, with a high PSNR of 98.264, a strong NCC value of 0.965, an exceptionally low NAE value of 0.046, and an impressive SSIM value of 0.983. Furthermore, the GPU implementation provides a remarkable overall speedup of 112 × for 256 × 256 color images. © 2024, The Author(s).

关键词： Contrast GPU Multi-secret Real-time Security

来源：评论

学校读者我要写书评

暂无评论

IoT-Based Automatic Gas Leakage Detection and Fire Protection System

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2022年第21期16卷 49-70页

作者： Islam, Gazi Zahirul Hossain, Md. Mobarak Faruk, Md. Nur, Fernaz Narin Hasan, Nayeem Khan, Khalid Mahbub Tumpa, Zerin Nasrin Department of Computer Science and Engineering Southeast University Dhaka Bangladesh Department of Computer Science and Engineering Daffodil International University Dhaka Bangladesh Department of Computer Science and Engineering Notre Dame University Bangladesh Dhaka Bangladesh School of Computer Science Western Illinois University IL United States Department of Computer Science and Engineering University of Information Technology & Sciences Dhaka Bangladesh

Gas Leakage and its fatal effects are a great concern throughout the world, especially in developing countries like Bangladesh. Every year lots of people died and countless damages to assets occur due to the fire caused by the gas leakage. Not only that but gas leakage and explosion are also very harmful to the climate. Thus, a system to detect gas leakage and preventive measures is of utmost importance. In this project, we design and implement an intelligent IoT prototype to detect gas leakage, and the fire caught by gas leakage. Our goal is to minimize the effect of gas leakage by taking some protective measures. When the gas sensor, detects the gas leakage, the solenoid valve shuts off the gas line, and the exhaust fan starts to run. Again, when the flame sensor detects a fire, the sucker throws the fire extinguisher balls at the fire. The GSM SIM module notifies the user by sending a message to his smartphone. The buzzer sounds when a mishap occurs and the LCD monitor always shows the status of the system. In this way, we have efficiently designed and implemented a low-cost and intelligent gas leak detection and fire suppression system. © 2022, International Journal of Interactive Mobile Technologies. All Rights Reserved.

关键词： Internet of things

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：