检索结果-内蒙古大学图书馆

Global Conference for Advancement in Technology (GCAT)

作者： Bandi Rupendra Reddy Daka Chandra Rup Mathi Rohith Meena Belwal Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (数字)9798350376685

ISBN: (纸本)9798350376692

Deepfake (manipulated images and videos) identification is critical in multimedia forensics, as it can spread misinformation, threaten privacy, and have legal implications. To address this problem, researchers and practitioners are developing deepfake detection techniques that use deep-learning models and computer vision algorithms to analyse the authenticity of images and videos. This study proposes a novel approach providing robust and scalable deepfake detection by using transfer learning in feature extraction and deep-learning models to train features extracted from the video dataset. The transfer-learning has been experimented with the ResNet, XceptionNet, and VGG16 models for feature extractions. Further, the deep-learning models Long short-term memory (LSTM) and Bidirectional long short-term memory (Bi-LSTM) have been experimented with to train the extracted features. To rigorously test the proposed approach, the data set under the experiment combined the three benchmark datasets - The Deepfake Detection Challenge (DFDC), Celeb-DF, and Face-Forensics++ datasets. The prediction rate achieved was 96 % and above on average by the proposed approach for the datasets under consideration for the experiments. The proposed approach performs better than the state-of-the-art techniques, gaining a higher accuracy of 96% and above.

关键词： Deep learning Deepfakes computer vision Privacy Computational modeling Forensics Transfer learning Streaming media Feature extraction Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Healthcare Waste Management: Leveraging Blockchain For Enhanced Efficiency and Transparency

Revolutionizing Healthcare Waste Management: Leveraging Bloc...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： G Venkat Sai Kumar C Rohith Reddy B.M Beena Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

The handling of healthcare waste poses substantial difficulties, such as inefficiency, lack of transparency, and failure to comply with regulations. This research examines a novel strategy for addressing these difficulties by using blockchain technology. Four smart contracts have been created to improve the effectiveness and clarity of hospital waste management procedures. These contracts are specifically created to automate the process of monitoring trash, guarantee compliance with regulations, and allow essential stakeholders to receive real-time data. In addition, the system analyses waste creation trends and detects any infractions committed by hospitals or factories, assessing if the concerns result from insufficient consumption or excessive output. The findings indicate that the integration of blockchain technology into hospital waste management may greatly enhance operational efficiency, guarantee compliance, and promote a more sustainable and transparent healthcare environment.

关键词： Waste management Hospitals Smart contracts Regulation Real-time systems Production facilities Blockchains Stakeholders System analysis and design Monitoring

来源：评论

学校读者我要写书评

暂无评论

A Scalable Machine Learning Model for Sales Forecasting using PySpark

A Scalable Machine Learning Model for Sales Forecasting usin...

引用

Knowledge engineering and Communication Systems (ICKECS), International Conference on

作者： Talluri Harshitha Simhadri Tanya Thadakaluru Jaswanthi Manju Venugopalan Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798350359688

ISBN: (纸本)9798350359695

Sales forecasting is a useful tool used for estimating future demand and sales. It provides insightful information for strategic decision-making, resource allocation, and inventory control. This research aims to utilize various machine learning algorithms for constructing a robust sales forecasting model, with the help of the Machine Learning library in PySpark. PySpark is chosen for its scalability, parallel processing framework, and seamless integration with machine learning libraries, making it an ideal choice for handling large datasets. MLlib is a powerful machine learning library within PySpark, offering a comprehensive set of scalable and distributed algorithms that enable efficient processing and analysis of large datasets. The research also incorporates time-series analysis. The performance of the research is evaluated using evaluation metrics R-Square(R2) value Root Mean Squared Error (RMSE) and Mean Squared Error (MSE), Mean Absolute Error (MAE). Out of all experimented models, Gradient Boosting Regressor stands out as the best-performing model with R-squared value of 0.93, showcasing its effectiveness in accurate sales predictions.

关键词： Measurement Knowledge engineering Machine learning algorithms Scalability Time series analysis Predictive models Parallel processing

来源：评论

学校读者我要写书评

暂无评论

Advancing of Microservices Architecture with Dockers

Advancing of Microservices Architecture with Dockers

引用

International Conference on computing and Networking Technology (ICCNT)

作者： Kriti Priya Sah Nikunj Jain Priyanshu Jha Jawed Hawari B.M Beena Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Docker has revolutionized web hosting. It offers efficiency, scalability, security, and automation. With Docker, businesses and individuals can simplify their hosting. With the help of Docker, the development process is simplified via managing to package the application into standardized units called containers. They can enhance website performance and contribute to a sustainable digital ecosystem. Micro-service architecture might be adopted for smooth flow for the development process. Resource optimization might get improved. Security measures could be bolstered. Multi-cloud deployment strategies may be explored. Server-less computing integration is a possibility. Containerized data storage solutions might be explored.. In the future, Docker based hosting could involve Kubernetes for container orchestration. Machine learning capabilities could be incorporated. Green computing initiatives might be implemented.

关键词： Scalability Ecosystems Microservice architectures Memory computer architecture Machine learning Containers Green computing Security Optimization

来源：评论

学校读者我要写书评

暂无评论

Protecting Data Mobility in Cloud Networks Using Metadata Security

引用

computer Systems science & engineering 2022年第7期42卷 105-120页

作者： R.Punithavathi M.Kowsigan R.Shanthakumari Miodrag Zivkovic Nebojsa Bacanin Marko Sarac Department of Information Technology M.Kumarasamy College of EngineeringKarur639113India Department of Computer Science and Engineering School of ComputingSRM Institute of TechnologyKattankulathur CampusChennai603203India Department of Information Technology Kongu Engineering CollegeErode638060India Singidunum University Belgrade11000Serbia

At present,health care applications,government services,and banking applications use big data with cloud storage to process and implement *** mobility in cloud environments uses protection protocols and algorithms to secure sensitive user ***,data may have highly sensitive information,lead-ing users to consider using big data and cloud processing regardless of whether they are secured are *** to sensitive data in cloud systems produce high risks,and existing security methods do not provide enough security to sensitive user data in cloud and big data *** present,several security solu-tions support cloud *** of them include Hadoop Distributed File Sys-tem(HDFS)baseline Kerberos security,socket layer-based HDFS security,and hybrid security systems,which have time complexity in providing security ***,mobile data security algorithms are necessary in cloud environ-ments to avoid time risks in providing *** our study,we propose a data mobility and security(DMoS)algorithm to provide security of data mobility in cloud *** analyzing metadata,data are classiﬁed as secured and open data based on their *** data are sensitive user data,whereas open data are open to the *** the basis of data classiﬁcation,secured data are applied to the DMoS algorithm to achieve high security in *** pro-posed approach is compared with the time complexity of three existing algo-rithms,and results are evaluated.

关键词： Data mobility data security cloud computing big data DMoS algorithm

来源：评论

学校读者我要写书评

暂无评论

Deepfake Image Forgery Detection using Local Feature Descriptors

Deepfake Image Forgery Detection using Local Feature Descrip...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： S Dienash T R Swapna Dept of Computer Science and Engineering Amrita School of Computing Coimbatore Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Deepfake Image Forgery,generates fake images after manipulating the original source images. This increases the risk of losing trust in images or videos. This paper proposes an efficient methodology to detect Deepfake images from real images. The methodology involves extracting Local Feature De scriptors(Local Binary Pattern (LBP),Frequency Decoded Local Binary Pattern (FDLBP),Binary Gabor Pattern (BGP)). The fusion of these features are fed to the DenseNet to classify the image as fake or real. The model uses Convolutional Neural Network (CNN) architecture that utilizes all three Local Feature Descriptors that extract features of the images. The model has an accuracy of $\mathbf{9 3. 6 5 \%}$ which is performing better than Deep learning models.

关键词： Training Deep learning Deepfakes Visualization Accuracy Scalability computer architecture Feature extraction Vectors Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Medical Record Security: Using Role-based Access Control, Digital Signatures, and RSA Encryption

Enhancing Medical Record Security: Using Role-based Access C...

引用

International conference of Electronics, Communication and Aerospace Technology (ICECA)

作者： Aditya Vijjapu Anusha P Alagawadi Anish Maddi C.R Kavitha Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (数字)9798350367904

ISBN: (纸本)9798350367911

Medicare, the proposed web application provides a unique way to store medical records in a secure manner by encrypting and providing role-based access control, where doctors can view the records of all patients but patients can view only their respective record and doctors also have the option of accessing RSA encrypted chat and also a unique digital signature is embedded to each record for ensuring the integrity of records. This provides a better approach for medical records management. Session management and secure authentication has also been implemented for tracking the actions that occurred in the website. The encrypted records are then stored in MongoDB. Therefore, this web-application provides a better and secure way to manage and share healthcare records.

关键词： Access control Protocols Authentication Medical services Aerospace electronics Encryption Time complexity Digital signatures Testing Postal services

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of ML & DL Models for Fetal Health Classification Using Cardiotocographic Data

A Comparative Analysis of ML & DL Models for Fetal Health Cl...

引用

Innovation in Technology (APCIT), Asia Pacific Conference on

作者： Tata Kaushik Tunuguntla Aasritha Sri Vani Vithyatharshana N Sangita Khare Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetam India

ISBN: (数字)9798350361537

ISBN: (纸本)9798350361544

Traditional diagnostic methods in fetal health are frequently hindered by class imbalance and complex data, which puts early intervention and optimal perinatal outcomes at risk. This study fills this important gap by conducting a thorough comparative analysis of several ML and DL models that have been effective in fetal health research. This project goes beyond the obvious applications and investigates how model performance is affected by Principal Component Analysis (PCA) and Chi-Square for feature extraction and feature selection respectively and Conditional Generative Adversarial Networks (CGANs) for data augmentation. This project seeks to determine the best model or ensemble for dependable and accurate fetal health prediction by methodically assessing model performance across all its forms, CGAN-augmented versions, integrated CGAN - PCA and CGAN - Chi-Square configurations. This will provide medical professionals with a data-driven tool for early diagnosis and well-informed clinical decisions. This thorough study has the potential to greatly enhance perinatal outcomes and improve the health of moms and their unborn children. It is positioned to transform prenatal care. In addition to identifying the best model, this comparative analysis lays the foundation for future research examining the integration of explainable AI techniques to gain deeper insights into fetal health dynamics and to understand the internal decision-making processes of the model.

关键词： Analytical models Technological innovation Pediatrics Transforms Predictive models Feature extraction Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Interactive Code Parsing and Expression Tree Visualization

Interactive Code Parsing and Expression Tree Visualization

引用

Innovative computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： Ve.Ram Akathya Yadukul Suresh Sahen Shivadutt Kavitha C.R. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

Binary information trees are key visualization and evaluation tools, particularly during the passing of algorithms and synthesizing designs. This paper is an interactive tool for producing binary information trees over time. This tool will allow the user to input variables, selected, truncating and then show the same as a binary tree. Using Network X and Matplotlib for graphing, this presents the user with an interactive pie chart to enable operator control and variable assignment. Dynamic information evaluation and substitution is supported; this allows for an immediate view of change when variables and functions are altered. It is aimed at user interaction with a didactic value, and with this in mind, it contributes to easier understanding of the fundamental issues of distributed algorithms, clustering, and information evaluation. Though derived from such existing tools as VMEXT and PAVT, it offers a simple, and thus very practical approach, becoming suitable for educational environments where a visualization shows better understanding of the abstract computer concepts.

关键词： Visualization Codes Input variables Education Debugging Binary trees Real-time systems Distributed algorithms Programming profession

来源：评论

学校读者我要写书评

暂无评论

Weapon Classification with Xception: An Efficient Deep Learning Approach

Weapon Classification with Xception: An Efficient Deep Learn...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Yeshwanth A R Bhuvaneswari Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India

Intelligent security systems require robust capabilities for weapon detection and classification. This study employs the Xception architecture, leveraging its unique features such as depth-wise separable convolutions and hierarchical feature extraction. A diverse dataset encompassing weapon and non-weapon entities is meticulously annotated and preprocessed. The Xception model is fine-tuned to effectively identify weapons, achieving notable results with an accuracy of 98.3%, precision of 98.50%, recall of 99.49%, and f1-score of 98.99%. Comparative evaluation with YOLOv8, ResNet50, and ResNet18 confirms Xception’s superiority in recognizing subtle weapon patterns. Rigorous evaluation on relevant datasets provides empirical evidence of the model’s effectiveness in real-world scenarios. These findings underscore Xception’s practical viability in enhancing security applications, contributing substantively to the discourse on advanced neural network architectures' role in addressing contemporary security challenges. This research emphasizes the importance of innovative approaches in augmenting security systems' capabilities to ensure public safety.

关键词：

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：