检索结果-内蒙古大学图书馆

5th International Conference on Information Management and Machine Intelligence, ICIMMI 2023

作者： Baskar, M. Kumar, Ankit Bajaj, Khushi Department of Computing Technologies School of Computing College of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Chengalpattu603203 India Department of Computer Science and Engineering School of Computing College of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Chengalpattu603203 India

ISBN: (纸本)9798400709418

In the field of emergency medical services, the element of time significantly influences patient outcomes. The groundbreaking Instant Ambulance Connection- Rescue Radar system is introduced to expedite responses to medical emergencies. This research paper explores the system's structure, approach, and potential impact, highlighting its role in providing swift and efficient emergency medical services. The primary objective of this system is to bridge the gap between patients and ambulance services, simplifying ambulance requests and hospital visit scheduling. A user-friendly Android app is central to its functionality, enabling one-tap ambulance requests and harnessing modern technologies like the Internet of Things and the Google Maps API to transmit user information and precise locations to local ambulance drivers rapidly. This system also empowers patients with real-time access to ambulance availability and the ability to track the ambulance's location in real-time. By enhancing communication between patients, ambulance drivers, and healthcare institutions, the system significantly improves the efficiency of the emergency medical response network. © 2023 ACM.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Survey on Network-based Covert Communication Techniques

Survey on Network-based Covert Communication Techniques

引用

2024 International Conference on Artificial Intelligence, Metaverse and Cybersecurity, ICAMAC 2024

作者： Alnuman, Rashed Hasan, Qusai Saadeh, Huda Department of Electrical Engineering & Computing Sciences Rochester Institute of Technology Dubai United Arab Emirates

ISBN: (纸本)9798350353488

Covert communications is the act of transmitting messages in a hidden or disguised manner. They have been utilized throughout history for a variety of purposes, ranging from espionage to personal privacy. Covert communication channels are intra-system channels that allow for the transmission of data without other parties knowing of their existence. The key concept is to hide the communication channel itself. Most channels leverage components of network protocols to increase the capacity of secret information sent. However, advanced monitoring and machine learning-based detection have made it increasingly difficult to conceal data. This means that to successfully set up covert communication channels, the sender and receiver have to be creative about how they encode and decode secret data. Many researchers have developed different covert channel schemes based on timing and storage techniques leveraging network protocols. This paper aims to investigate all recent network covert communication schemes in accordance with criteria and scrutinize their weaknesses and detection methods. We find that a storage-based approach with custom encoding and leveraging recommended protocol produces the best results when designing a covert channel scheme. © 2024 IEEE.

关键词： channel covert communication detection survey

来源：评论

学校读者我要写书评

暂无评论

An Early Lung Disease Detection and Classification Using Bidirectional Deep Learning Over Masked Autoencoder

An Early Lung Disease Detection and Classification Using Bid...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Ramadevi, M. Ramkumar, M.O. Jayakumar, D. Rajmohan, R. Arunkumar, A. Ifet college of Engineering Villupuram India Srm Institute of Science and Technology Department of Computing Technology Kattankulathur campus Tamilnadu India

ISBN: (纸本)9798331509828

Around the world., lung diseases like Pneumonia., lung nodule infiltration., pneumothorax are the main cause of death and severe health problems. In this digital world., many new technologies were developed for early and accurate detection of lung disease but many of the technologies are not able to predict the lung disease accurately and required large amount of labelled data. This paper describes a new approach by combining bidirectional deep learning and masked autoencoders for lung disease detection and classification from medical images. The masked autoencoder learns meaningful representations by reconstructing masked regions in lung images., while bidirectional deep learning model context from both directions., improving disease detection accuracy This algorithm doesn't required large labelled data it can learns from unlabelled data. The main purpose of this algorithm is used to learn effective representation of medical images by masking parts of input data and reconstructing them. which are crucial for accurate disease detection and classification. The proposed Bidirectional deep learning framework combines forward & Backward propagation process to enchance the learning efficiency and robustness of the lung images. This methodology detect and classify the disease like pneumonia., lung nodule., pneumothorax., infiltration and other lung diseases. Experimental results show significant improvements in sensitivity and specificity., especially in cases with subtle abnormalities in the lung tissue. © 2025 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Artificial gannet optimization enabled deep convolutional neural network for autism spectrum disorders classification using MRI image

引用

Multimedia Tools and Applications 2024年第30期83卷 74757-74783页

作者： Prasad, Vadamodula Ganeshan, R. Rajeswari, R. Department of Computer Science & amp Engineering Lendi Institute of Engineering & ampTechnology Jonnada Village Andhra Pradesh Vizianagaram District 535005 India School of Computing Science and Engineering VIT Bhopal University Kothrikalan Madhya Pradesh Sehore466114 India Department of Electronics and Communication Engineering Rajalakshmi Institute of Technology Chennai India

Autism Spectrum Disorder (ASD) is a neurodevelopment-based disability caused by variations in the brain. This may cause impact on social skills and communication of an individual. Autism is a highly challenging issue to diagnose at the early stages. ASD is one of the important problems to diagnose because it starts manifesting at low ages. This paper aims at ASD classification using MRI Images by Artificial Gannet Optimization enabled Deep Convolutional Neural Network (AGO_DCNN). Here, an MRI image is assumed that be subjected to pre-processing of the image and feature extraction phases as an input. The bilateral filter is employed to remove the noises from the input MRI image and in the pre-processing of an image stage Region of Interest (ROI) extraction is conducted. The pivotal region extraction phase receives a filtered image after which AGO is used to extract the pivotal region. AGO is a newly designed approach by merging two optimizations namely Artificial Ecosystem-based Optimization (AEO) and Gannet Optimization Algorithm (GOA). At the same time, features are extracted from the input image during the feature extraction stage. In a feature extraction stage, some features like texture and statistical features are extracted. At last, the classification of ASD is conducted using DCNN, wherein by AGO the classifier is tuned. Furthermore, AGO_DCNN attained better outcomes in terms of maximal True Positive Rate (TPR), True Negative Rate (TNR), and accuracy values of about 93.7%, 90.8%, 96.8% and False Positive Rate (FPR) and minimal False Negative Rate (FNR) and values of 78.7% and 74.7%. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Enhancing intrusion detection in IIoT: optimized CNN model with multi-class SMOTE balancing

引用

Neural computing and Applications 2024年第24期36卷 14643-14659页

作者： Eid, Abdulrahman Mahmoud Soudan, Bassel Nassif, Ali Bou Injadat, MohammadNoor Department of Computer Engineering College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Department of Data Science and AI Faculty of Information Technology Zarqa University Zarqa Jordan

This work introduces an intrusion detection system (IDS) tailored for industrial internet of things (IIoT) environments based on an optimized convolutional neural network (CNN) model. The model is trained on a dataset that was balanced using a novel multi-class implementation of synthetic minority over-sampling technique (SMOTE) that ensures equal representation of all classes. Additionally, systematic optimization will be used to fine tune the hyperparameters of the CNN model and mitigate the effects of the increased size of the training dataset. Evaluation results will demonstrate substantial improvement in performance when the optimized CNN model is trained on the balanced dataset. The proposed IDS will be evaluated using the IIoT-specific WUSTL-IIOT-2021 dataset, and then its generalization capability will be verified using the non-domain specific UNSW_NB15 dataset. The model’s performance will be evaluated using accuracy, precision, recall, and F1-score metrics. The results will demonstrate that the proposed IDS is highly effective with performance exceeding 99.9% on all performance metrics. The IDS is also highly effective in detecting intrusion for generic IT networks achieving improvements in excess of 30% compared to the default baseline model. The results emphasize the versatility and effectiveness of the proposed IDS model, making it a reliable and adaptable solution for enhancing network security across diverse network environments. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

MGRU-M1dCNN: A Hybrid Model for Stock Price Prediction 15

MGRU-M1dCNN: A Hybrid Model for Stock Price Prediction

引用

15th International Conference on Computer and Automation engineering, ICCAE 2023

作者： Kanwal, Anika Chandrasekaran, Siva Technologies Swinburne University of Technology Department of Computing Technologies School of Science Computing and Engineering Melbourne Australia

ISBN: (纸本)9798350396225

Predicting the stocks price is both intriguing and difficult due to the nonlinear and noisy stock's data. Stock investors' investment risk can reduce and their return on investment can be significantly increased by properly predicting the change in stock prices. It is challenging for researchers to forecast stock prices using an individual stock forecasting model. Therefore, in this research we proposes MGRU-M1dCNN, a hybrid model to predict the stock opening price of the next day. This model is consisted of multiple gated recurrent unit (MGRU) and Multiple single dimensional convolutional neural networks (M1dCNN). MGRU employs to extract the valuable feature patterns from opening price of stocks. M1dCNN is used to extract the spatial features of the inputs received from MGRU to predict the stock prices. The outcomes demonstrate that this technique performs best, with the least Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) which are 0.854 and 0.456. When compared to other GRU based models (GRU-CNN, GRU-DNN, and GRU), the MGRU-M1dCNN model is better suited for stock price forecasting and for providing investors a trustworthy means to choose which stocks to buy. © 2023 IEEE.

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Intelligent Digital Credentialing System for Participatory Governance: Design, Implementation, and Potential Implications

引用

SN Computer Science 2024年第8期5卷 1051页

作者： Dhasarathan, Chandramohan Rajaguru, Dayalan Subash Chandra Bose, J. Department of Electronics and Communication Engineering Thapar Institute of Engineering and Technology Punjab Patiala India Department of Information Technology Perunthalaivar Kamarajar Institute of Engineering and Technology Karaikal Puducherry India School of Computing Science and Engineering VIT Bhopal University Madhya Pradesh Bhopal India

This research proposes a blockchain-based digital credentialing system for participatory governance to address issues with centralized, opaque, and insecure standard credential systems. Leveraging the Hyperledger Fabric platform and smart contracts, the proposed method increases credential data’s transparency, security, and immutability, resulting in a more efficient and cost-effective solution. The paper covers the technological design of the system, including the use of Hyperledger Fabric components and the incorporation of the digital credential system. It also discusses the potential benefits and challenges of the system, highlighting its potential to increase trust and accountability in participatory governance. This paper presents a promising solution for improving digital credentialing using blockchain technology with implications for participatory governance. It explores a participatory administration’s social and political consequences via a blockchain-enabled innovative certification system, including greater citizen engagement and participation and enhanced credibility and legitimacy of governance processes. However, it acknowledges data privacy issues and potential power imbalances. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Artificial intelligence Blockchain technology Digital credentialing system Hyperledger Smart contract

来源：评论

学校读者我要写书评

暂无评论

Loan Repayment Predictive Model Using Ensemble Algorithm

Loan Repayment Predictive Model Using Ensemble Algorithm

引用

2024 IEEE SmartBlock4Africa, SmartBlock4Africa 2024

作者： Godwin Akinbayo, O. Akintola Kolawole, G. Adewole David, B. School of Computing Federal University of Technology Department of Software Engineering Ondo State Akure Nigeria

ISBN: (纸本)9798350376838

The accurate prediction of loan repayment ability is paramount in any financial industry to minimize risks and enhance decision making. This project centers on the development of a loan repayment predictive model using ensemble algorithm. The performance of the algorithm is evaluated through the following metrics: f1 score, accuracy, and precision. Five classifiers including Random Forest, AdaBoost, Gradient Boosting, Logistic Regression, and SVC were used as base classifiers for the ensemble. Ensemble-based optimization (using RSCV) is employed to get the best combination of hyperparameters. This technique performs a randomized search over specified hyperparameter values, using cross-validated performance to find the best combination to create models that make up the ensemble model. Preliminary results indicate promising performance improvements when compared to single model. Future research in this domain could further refine the model and expand its applications in the ever-evolving financial sector. © 2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Web applications testing techniques: a systematic mapping study

引用

International Journal of Web engineering and technology 2023年第4期17卷 372-412页

作者： Hanna, Samer Ahmad, Amro Al-Said Department of Software Engineering Faculty of Information Technology Philadelphia University Jordan School of Computing and Mathematics University of Keele United Kingdom

Due to the importance of web application testing techniques for detecting faults and assessing quality attributes, many research papers were published in this field. For this reason, it became essential to analyse, classify and summarise the research in the field. To achieve this goal, this research conducted a systematic mapping study on 98 research papers in the field of web applications testing published between 2008 and 2021. The results showed that the most commonly used web applications testing techniques in literature are model-based testing and security testing. Besides, the most commonly used models in model-based testing are finite-state machines. The most targeted vulnerability in security testing is SQL injection. Test automation is the most targeted testing goal in both model-based and security testing. For other web applications testing techniques, the main goals of testing were test automation, test coverage, and assessing security quality attributes. Copyright © 2022 Inderscience Enterprises Ltd.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Security of Images Using Pascal's Triangle Chaotic Encryption Scheme and with Biometric Authentication in Cloud Storage 4

Security of Images Using Pascal's Triangle Chaotic Encryptio...

引用

4th International Conference on Advances in Electrical, computing, Communication and Sustainable Technologies, ICAECT 2024

作者： Gupta, Raghav Gullapalli, Manasa Suseela, G. School of Computing Science and Engineering Srm Institute of Science and Technology Department of Networking and Communications Tamil Nadu Kattankulathur603203 India School of Computing Science and Engineering Faculty of Engineering and Technology Srm Institute of Science and Technology Department of Networking and Communications Tamil Nadu Kattankulathur603203 India

ISBN: (纸本)9798350343670

A key component of cloud computing is cloud storage, which allows data to be stored on remote servers. The result is a reduction in the amount of storage space required on local devices, allowing data to be accessed from anywhere with an internet connection. Furthermore, cloud storage is more secure than local storage due to the use of encryption and other security measures by professional providers. This is a practical and cost-effective solution to store large images required to be safeguarded from malicious black hat hackers. Images are the most valuable yet vulnerable form of data that can be used to track down user activities and taken advantage by hackers, used to commit identity theft, fraud. Issues concerning the security and privacy of images saved in the cloud have arisen as cloud storage has grown in popularity. The proposed method will focus on the encryption of images using a chaotic encryption scheme based on Pascal's triangle. The user will authenticate their identity before uploading images to cloud storage and likewise confirm their authentication in the process of retrieval of an image. Such a secure system is better than traditional security methods for password settings as it cannot be easily stolen. Additionally, this method is more secure than other methods due to its complex encryption mechanisms, making it impossible to guess or steal the encryption key. In addition to providing extra security for sensitive images, biometric authentication will offer a stronger method of verifying and validating users on the cloud. © 2024 IEEE.

关键词： AWS Rekognition Chaotic systems Cloud Security Confusion Diffusion Facial Authentication Image Encryption Image Shuffling Pascal's Triangle Transform

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：