检索结果-内蒙古大学图书馆

1st International Conference on Emerging Technologies for Dependable Internet of Things, ICETI 2024

作者： Al-Dilami, Redwan Zahary, Ammer T. Al-Sharafi, Abobakr Al-Anashi, Osamah Maresh, Suliman Faculty of Computing and TT University of Science and Technology Sana’a Yemen

ISBN: (纸本)9798331533557

Facial recognition technology has emerged as a pivotal tool in both security and technical domains. Its adoption has accelerated in several developed nations, where it finds applications across various sectors. For instance, institutions and businesses leverage this technology to monitor employees and detect unauthorized individuals, while banks utilize it to verify identities during cash withdrawals, serving as an alternative to traditional ATM cards. In this context, our research aims to propose a machine learning-based method for improving facial recognition accuracy. We conducted a thorough review of existing algorithms in the field and identified Support Vector Machine (SVM) and Principal Component Analysis (PCA) as the most effective based on prior studies. To evaluate these algorithms, we compared SVM and PCA in the context of identity verification. Our experiments involved training the algorithms on a dataset comprising 5,749 facial images. The results demonstrated that the SVM algorithm significantly outperformed PCA in terms of accuracy. We believe that the successful application of the SVM algorithm can provide substantial benefits to institutions looking to enhance their security measures through reliable facial recognition systems. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Application of CNN Based Deep Learning Algorithm for Herbal Plant Leaf Detection

Application of CNN Based Deep Learning Algorithm for Herbal ...

引用

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

作者： Pongiannan, R.K. Das, Sagardeep Purbia, Rudra Prakash Brindha, R. Jame, S. Lourde Shiju Kumar, P.S. Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur India

ISBN: (纸本)9798331509828

The medicinal plant market faces challenges due to inefficiencies and a lack of transparency. In this paper, a total of 10GB dataset with 10,000 entries, including 15 attributes such as plant name, region, price, and high-resolution images capture seasonal and geographical variations. Designed for precise plant identification and market forecasting, the dataset also contains metadata and historical data on prices and demand trends. Deep learning models, including recurrent neural networks (RNN) and convolutional neural networks (CNNs), are employed for accurate plant identification. Time series analysis is used to forecast market patterns. Data optimization techniques are applied to ensure real-time insights, allowing farmers and traders to make informed decisions. This system aims to enhance market transparency and improve the decision-making process in the medicinal plant industry. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Detection and Classification of Monkeypox Disease with Chatbot 3

Detection and Classification of Monkeypox Disease with Chatb...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Chandu, P. Siddardha, P. Priyadharshini, K. Department of Computing Technologies SRM Institute of Science and Technology Kattankulathur India

ISBN: (纸本)9798331527549

Monkeypox detection is essential for effective public health management and controlling its spread. Timely detection enables early intervention in outbreaks, reducing transmission risk. This project presents an innovative framework that enhances monkeypox detection and classification using deep learning and an interactive chatbot. It employs the VGG16 convolutional neural network (CNN) for accurate classification of monkeypox from medical images, utilizing performance metrics like precision, recall, and F1 score for reliability. Additionally, the system includes a neural network-based chatbot that provides interactive assistance, answers user questions, offers symptom information, and guides users through the diagnostic process. This chatbot improves user engagement and accessibility, linking clinical diagnostics with patient interaction. Built on the Flask framework, the system ensures a smooth, user-friendly interface for both image classification and chatbot functionalities. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Methods for Secure Medical Image Transfer: Encryption and Standardization Techniques

Comprehensive Methods for Secure Medical Image Transfer: Enc...

引用

2024 International Conference on science, technology, Engineering and Management, ICSTEM 2024

作者： Priyadharshini, K. Nandi, Hitesh Parmar, Harsh Dept. of Computing Technologies School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai India

ISBN: (纸本)9798350376913

The primary goal of the process is to securely transfer medical images. This involves utilizing MRI datasets for processing and applying resizing and filtering techniques such as Conv2D and Gaussian blur to standardize the images. Additionally, an attack model is developed to enhance information security, starting with a PGD attack to access model weights and followed by a DAG attack to increase loss functions. Encryption is then performed using a Chaos-based encryption model to create a chaotic map and the Henon map for image conversion. A randomly generated key encryption method is utilized to generate a key for secure transfer. The encrypted image is displayed, and in the receiver section, the process is reversed for decryption by inputting the key generated in the encryption model. Finally, the original medical image is retrieved along with parameters such as MSE, MAE, RMSE, and F2 score to assess the accuracy of the recovered image and ensure its correctness. © 2024 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Explainable AI in Large Language Models: A Review 2

Explainable AI in Large Language Models: A Review

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Sauhandikaa, S. Bhagavath Narenthranath, R. Sathya Bama Krishna, R. Sathyabama Institute of Science and Technology School of Computing Chennai India

ISBN: (纸本)9798331534950

Explainable AI in Large Language Models (LLMs) represents an exciting frontier in Artificial Intelligence. In recent times, LLMs provides various AI applications ranging from chatbots to content generation. While these applications are exciting, their decision-making process behind the intelligent systems plays a major role. These processes are also a mystery and they operate as "Black boxes", where the processes are often challenging to interpret. This paper helps to give a sense of the processes that occurs behind these decisions. It helps to understand why the AI has chosen one sentence rather than the other. It explores key breakthroughs of XAI techniques that helps in solving these complexities. Methods such as Attention Visualization, Feature Importance Analysis and Counterfactual Explanations provide insights on why certain decisions are made. These techniques provide a voice to the intricate processes and address real-world challenges, which makes it more reliable. This enables better transparency and makes it trust-worthy. XAI has the potential to address ethical concerns, enhance user trust and improve Human-AI collaboration. This research highlights how better transparency in AI is not merely a technical challenge but a foundational step towards building a future where humans and AI work together seamlessly and responsibly. © 2024 IEEE.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Multi-dataset learning with channel modulation loss for blind image quality assessment

引用

Multimedia Tools and Applications 2024年第40期83卷 88159-88178页

作者： Li, Hui Yan, Zhaoyi Fan, Xiaopeng Department of Computing Science Harbin Institute of Technology Harbin China Department of Network Intelligence Pengcheng Laboratory Shenzhen China

In Blind Image Quality Assessment (BIQA), due to the problem of laborious labeling, it is perceived as the intractability of collecting a new large-scale dataset that has plentiful images with a large diversity in distortion and scene. Therefore, to develop a general model, training with data from diverse datasets could be a viable solution and hold significant value. A straightforward solution is to mix multiple datasets to train a robust model. However, as IQA datasets vary in terms of distortion types and labeling mechanisms, models fail to adapt well across various datasets. To solve the multi-dataset adaption problem, we propose a Channel Modulation Loss that encourages each channel to adaptively enhance/diminish dataset-corresponding features. In detail, when training a CNN with data from all the datasets, certain channels acquire knowledge that can be applied across some datasets, whereas others are only effective for a specific dataset. Therefore, we propose a dataset-specific kernel as supervision, by which channel attention can be explicitly optimized to emphasize the channels corresponding to the dataset of an input image. Finally, extensive experiments on six IQA databases show the promise of the learned method in blindly assessing image quality. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

Big Data analytics for privacy through ND-homomorphic encryption

引用

Journal of Control and Decision 2023年第1期10卷 64-71页

作者： S.Saravanan N.Poornima Department of CSE SRM Institute of Science and TechnologyChennaiIndia Department of Data Science and Business Systems School of ComputingSRM Institute of Science and TechnologyKattankulathurIndia

Rapidly rising the quantity of Big Data is an opportunity to flout the privacy of people. Whenhigh processing capacity and massive storage are required for Big Data, distributed networkshave been used. There are several people involved in these activities, the system may contributeto privacy infringements frameworks have been developed for the preservation of privacy atvarious levels (e.g. information age, information the executives and information preparing) asfor the existing pattern of huge information. We plan to frame this paper as a literature surveyof these classifications, including the Privacy Processes in Big Data and the presentation of theAssociate Challenges. Homomorphic encryption is particularised aimed at solitary single actionon the ciphered information. Homomorphic enciphering is restrained to an honest operation onthe encoded data. The reference to encryption project fulfils many accurate trading operationson coded numerical data;therefore, it protects the written in code-sensible information evenmore.

关键词： Security and confidentiality vast statistics data encryption nondeterministic fully homomorphic encryption

来源：评论

学校读者我要写书评

暂无评论

Empowering Inquisitive Learners: ICT and Holistic Development in University 5.0 13

Empowering Inquisitive Learners: ICT and Holistic Developmen...

引用

13th IEEE International Conference on Teaching, Assessment and Learning for Engineering, TALE 2024

作者： Rajagopal, Balaji Ganesh Kannan Raju, Jagadeesh Jacob, Mincy Rachel Srm Institute of Science and Technology School of Computing Tiruchirappalli India

ISBN: (纸本)9798350376234

University 5.0 thrives on the transformative power of ICT. Digital learning platforms, virtual labs, and collaborative software elevate the educational experience by fostering creativity and inclusivity. These tools reshape how universities operate: interactive platforms engage students through simulations and readily available materials, while virtual labs provide safe and cost-effective experimentation opportunities. Research is empowered as well, with cloud storage and advanced software accelerating data analysis and collaboration. Online repositories democratize research findings, fostering knowledge exchange and scientific progress. Administration becomes streamlined with online registration, payments, and transcripts minimizing bureaucratic hurdles. Automated workflows further optimize internal processes, allowing staff to dedicate more time to fostering a dynamic learning environment. Finally, ICT bridges the gap between universities and the broader community. Online courses and events connect institutions with alumni, industry leaders, and the public, enriching the overall learning experience. In essence, ICT propels universities towards a more adaptable, responsive, and sustainable educational model, preparing students to thrive in a rapidly evolving world. This work delves into the different verticals in an educational management system in which ICT tools can be introduced to transform the university towards practicing holistic development. Three different architectures are proposed in this article to universalize the teaching-learning process along with holistic development to achieve the requirements for University 5.0. © 2024 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Deep Guard Authenticator 15

Deep Guard Authenticator

引用

15th International Conference on Advances in computing, Control, and Telecommunication Technologies, ACT 2024

作者： Das, Deepshikha Sarkar, Shreyan Rizvi, Hamid Shobana, M. SRM Institute of Science and Technology School of Computing Chennai India

ISBN: (纸本)9798331300579

A novel method for detecting deepfakes by presenting an AI architecture that is dynamic and adaptable and is designed and exclusively for picture authentication. Conventional deepfake detection models frequently find it difficult to adjust to the quickly changing methods of deepfake generation. As a result, our suggested system adopts a dynamic learning approach and makes use of unsupervised learning concepts to update its comprehension of novel manipulation patterns regularly. The inclusion of a self-updating neural network architecture that gains knowledge from a continuously changing data set constitutes the fundamental innovation. This solution eliminates the need for regular manual updates and guarantees that the model continues to be successful against new deepfake techniques. During the identification phase, the system uses a new attention mechanism that dynamically focuses on important parts inside an image and adjusts its analysis based on real-time insights. It also highlights the integration of uncertainty quantification and explainability in the detection process. Transparency and user confidence are ensured by an interpretable attention map, which offers insights into the model's decision-making process. To provide a more nuanced view of the detection certainty, the framework also includes uncertainty estimates that quantify the model's confidence in its predictions. The suggested system marks a substantial advancement in the field of deepfake detection by embracing dynamism, adversarial collaboration, and transparency. We empirically evaluate our technique and its superior adaptability and effectiveness in protecting the integrity of visual content in an era of increasingly complex synthetic media. © Grenze Scientific Society, 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A review on network function virtualisation security challenges and design considerations

引用

International Journal of Networking and Virtual Organisations 2024年第4期31卷 368-393页

作者： Ahmad, Naveed Rathore, Muhammad Siraj Ngadi, Md Asri bin Faculty of Engineering University Teknologi Malaysia 81110 Malaysia Faculty of Computing Department of Computer Science Capital University of Science and Technology Islamabad46000 Pakistan

Network function virtualisation (NFV) offers several benefits to both network operators and end users. It is a more programmable and low-cost solution as compared to a traditional network. Since the network functions are implemented in software, there is a great opportunity of extending a network according to the changing requirements of the customers. However, at the same time, there are many security threats since the same commodity hardware is shared among multiple virtualised network functions. In literature, various NFV security threats are reported. In this work, our aim is to consolidate them in a more structured and organised manners. We highlight the different building blocks of a NFV framework and then explore how a particular component may become the victim of an attacker. Finally, we summarise our lesson learned and present open research issues which might be useful for NFV practitioners and researchers. © 2024 Inderscience Enterprises Ltd.

关键词： Network function virtualization

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：