检索结果-内蒙古大学图书馆

4th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2023

作者： Sannala, Gayatri Sanjana Rohith, K.V.G. Vyas, Aashutosh G. Kavitha, C.R. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru560035 India

ISBN: (纸本)9789819965854

Artificial intelligence (AI) has the potential to revolutionize the field of healthcare by automating many tasks, enabling more efficient diagnosis and treatment. However, one of the challenges with AI in healthcare is the need for explainability, as the decisions made by these systems can have serious consequences for patients. AI can be particularly useful in the classification of diseases based on symptoms. This involves using machine learning algorithms to analyze a patient’s symptoms and classify them as having a particular disease or condition. While using black box machine learning algorithms can be highly accurate, there is little to no understanding on how these models work. Therefore, using techniques such as feature importance analysis and Explainable AI, it is possible to provide clear explanations for the decision-making process, which can improve trust and understanding among healthcare providers and patients. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Identity Management Dapp using Ethereum Blockchain and IPFS 15

Identity Management Dapp using Ethereum Blockchain and IPFS

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Avvaru, Ananya Aaditi Tandon, Aryan Beena, B.M. Amrita Vishwa Vidyapeetham Amrita School of Computing Bengaluru Department of Computer Science & Engineering Bangalore India

ISBN: (纸本)9798350370249

This paper explores the integration of a verification and document management DApp into the core of the Ethereum blockchain and the InterPlanetary File System (IPFS). This way, the multi-signature wallets and intelligent contracts introduced help restore many traditional problems based on the secure handling of documents and ensure increased security, data integrity, and easily accessible documents. This DApp will allow such safe, transparent interaction that mandates consensus with multi-sig functionalities during document transactions to ensure the immutability and retrievability of those documents. This implies that the solution would scale using Ethereum and IPFS while offloading pressure off the blockchain to assure high data availability and reliability. Recent performance reviews indicate relevant improvements in the processes related to document management, and this improvement may even have broader implications for the filling implementation in essential sectors that need both a secure and efficient document-handling process. © 2024 IEEE.

关键词： Blockchain DApp Ethereum IPFS

来源：评论

学校读者我要写书评

暂无评论

An Integrated Study on Convolutional Neural Networks and Graph Neural Networks for Brain Tumor Classification from MRI Images 2024

An Integrated Study on Convolutional Neural Networks and Gra...

引用

16th International Conference on Contemporary computing, IC3 2024

作者： Ashok, Asha Hitesh, Odulapalli Naidu, Gonuguntla Praveen Abhinav, Beeneedi Krishna, Chitirala Pranav Vamsi Nair, Manjusha Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Kerala Amritapuri India

ISBN: (纸本)9798400709722

Brain tumors are one of the top diseases with less survival rate that affect humans across the globe and the development of brain tumors is influenced by many factors. The abnormal growth of cell masses in different categories of brain tumors are detected using brain Imaging techniques such as Magnetic Resonance Imaging(MRI). The purpose of this study is to examine the potential of Graph Convolutional Networks (GCNs) combined with pre-trained Convolutional Neural Network(CNN) models for brain tumor classification. Novel architectures, including VGG16, Densenet121, and Resnet18, are used to harness hierarchical features learned by CNNs and exploit graph-based representations for tumor classification. The models showed accuracy ranging from 64 to 74% and Resnet18 showed improved feature extraction compared to other models. The findings of this study highlight the models' efficacy in leveraging image features by using the pre-trained CNN models like VGG16, DenseNet121, and ResNet18 to extract rich hierarchical features from brain tumor MRI images. These extracted image features are then transformed into graph structures, enabling the application of Graph Convolutional Networks (GCNs) for classification tasks. By incorporating spatial dependencies among features through GCNs, the models can effectively learn complex patterns and relationships within the image data, leading to accurate brain tumor classification results. Visual representations using PCA offer insights into distinctive feature representations learned by each model, underscoring the significance of model architecture and backbone selection in GCN based medical image analysis. Future work aims to explore larger datasets, refine hyperparameters, and delve into interpretability aspects, further advancing GCNs' role in medical imaging and diagnostics. © 2024 Copyright held by the owner/author(s).

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Advanced deep learning approach for enhancing crop disease detection in agriculture using hyperspectral imaging

引用

Journal of Intelligent and Fuzzy Systems 2024年第2期46卷 3281-3294页

作者： Zekrifa, Djabeur Mohamed Seifeddine Lamani, Dharmanna Chaitanya, Gogineni Krishna Kanimozhi, K.V. Saraswat, Akash Sugumar, D. Vetrithangam, D. Koshariya, Ashok Kumar Manjunath, Manthur Sreeramulu Rajaram, A. Department of Bioinformatics Higher School of Food Science and Agri-Food Industry Ahmed Hamidouche Av Oued Smar Algiers Algeria Department of Computer Science & Information Technology School of Computing and Information Technology REVA University Rukmini Knowledge Park Kattigenahalli Karnataka Bengaluru India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil Nadu Chennai India Department of Computer Science Engineering Dr. K. N. Modi University Jaipur Rajasthan Newai India Department of Electrical and Electronics Engineering Karunya Institute of Technology and Sciences Deemed to be University Coimbatore India Department of Computer Science and Engineering University Institute of Engineering Chandigarh University Punjab Mohali India Department of Plant Pathology School of Agriculture Lovely Professional University Punjab Phagwara India Department of Electronics and Communication Engineering E.G.S. Pillay Engineering College Tamilnadu Nagapattinam India

Crop diseases pose significant challenges to global food security and agricultural sustainability. Timely and accurate disease detection is crucial for effective disease management and minimizing crop losses. In recent years, hyperspectral imaging has emerged as a promising technology for non-destructive and early disease detection in crops. This research paper presents an advanced deep learning approach for enhancing crop disease detection using hyperspectral imaging. The primary objective is to propose a hybrid Autoencoder-Generative Adversarial Network (AE-GAN) model that effectively extracts meaningful features from hyperspectral images and addresses the limitations of existing techniques. The hybrid AE-GAN model combines the strengths of the Autoencoder for feature extraction and the Generative Adversarial Network for synthetic sample generation. Through extensive evaluation, the proposed model outperforms existing techniques, achieving exceptional accuracy in crop disease detection. The results demonstrate the superiority of the hybrid AE-GAN model, offering substantial advantages in terms of feature extraction, synthetic sample generation, and utilization of spatial and spectral information. The proposed model’s contributions to sustainable agriculture and global food security make it a valuable tool for advancing agricultural practices and enhancing crop health monitoring. With its promising implications, the hybrid AE-GAN model represents a significant advancement in crop disease detection, paving the way for a more resilient and food-secure future. © 2024 – IOS Press. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Advanced Schedulability Testing for Adaptive Mixed-Criticality Systems under Weakly Hard Real-Time Constraints 5

Advanced Schedulability Testing for Adaptive Mixed-Criticali...

引用

5th CPSSI International Symposium on Cyber-Physical Systems (Applications and Theory), CPSAT 2024

作者： Rabbiun, Hossein Mohammadi, Jamal Shirazi, Mahmoud Kargahi, Mehdi Department of Computer Science and Information Technology Zanjan Iran University of Tehran School of Electrical and Computer Engineering College of Engineering Tehran Iran

ISBN: (纸本)9798331529284

This paper advances the schedulability analysis of the Adaptive Mixed-Criticality for Weakly Hard Real-Time Systems (AMC-WH) which allows a specified number of consecutive low-criticality (LO) jobs of tasks to be skipped when the system operates in the high-criticality (HI) mode. The current AMC-WH schedulability test, based on the skip-over model, in which low tasks are guaranteed to meet m-s out of m consecutive deadlines, where s is the number of allowed skips and m is the cycle length, only calculates the worst-case response times (WCRT) for low tasks under a fixed execution pattern post-mode switch. To address this limitation, we propose a new sufficient schedulability test for AMC-WH using the (m,k)-firm model, which allows various execution patterns for low tasks after a mode switch, enhancing the flexibility and applicability. Additionally, we develop an exact schedulability test for AMC-WH based on response time analysis (RTA). This test modifies the existing exact tests for the AMC algorithm, incorporating updates to state-space exploration and pruning rules to account for low task execution after a mode switch. Simulation results validate the effectiveness of our tests, demonstrating enhanced schedulability analysis and optimized resource allocation. © 2024 IEEE.

关键词： Space research

来源：评论

学校读者我要写书评

暂无评论

A Novel Zero-Knowledge Authentication Protocol for Secure Communication in VANET 15

A Novel Zero-Knowledge Authentication Protocol for Secure Co...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Vinod, Ardra Pranav, Mayur S.V. Vinodkumar, Malavika Remyakrishnan, P. Department of Computer Science and Engineering Amrita School of Computing Coimbatore Amrita Vishwa Vidyapeetham 641112 India

ISBN: (纸本)9798350370249

Vehicular Ad Hoc Network (VANET) is a particular subclass of the mobile ad-hoc network that raises several security challenges, notably how users authenticate the network. The work explores using zero-knowledge proofs for secure authentication while preserving user privacy and aims at encrypted information exchange between onboard units. Zero-knowledge proofs enhance security by protecting against impersonation attacks. We strive to reduce the dependence on roadside units for computational tasks by integrating the central authentication server and sub-authentication servers. We reduce modular exponentiation operations during authentication, enhancing efficiency without compromising security. We use the protocol verifier tool called Proverif to verify the security of our protocol. Simulation using the NS-2 simulator validates the protocol by varying the vehicle density. This paper advances VANET security by combining zero-knowledge authentication with encrypted information exchange, strengthening security, efficiency, and data confidentiality while reducing reliance on RSUs. Our protocol ensures secure communication in VANET with minimum computational and communication overhead. ©2024 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

ML Based Light-Weight Security Protocol for IoFT Device 6

ML Based Light-Weight Security Protocol for IoFT Device

引用

6th International Conference on Robotics and Automation in Industry, ICRAI 2024

作者： Khan, Awais Aziz, Ayesha Tariq, Muhamad Kamal, Mohsin National Univeristy of Computer and Emerging Sciences Department of Electrical Engineering Islamabad Pakistan School of Computer Science National Univeristy of Computer and Emerging Sciences Islamabad Pakistan School of Electrical Engineering and Computer Science National Univeristy Science and Technology Islamabad Pakistan

ISBN: (纸本)9798350355703

Forest plays a vital role in environmental change and the protection of forests is the utmost important thing. The study attempts to suggest a solution for a smart forest (Internet of Forest Things). As nowadays, the Internet of Things is emerging very vastly and a large number of researchers are working towards the field of Internet of Forest Things (loFT). The protection of smart forests is of utmost importance because the infrastructure is physically unprotected and they generate huge data about the forest. Due to scalability, smart forest controllers are small-sized and low-cost devices with less computational capabilities. Keeping it in mind, the designed algorithms should be lightweight so that they can meet the requirements. To address this issue, this paper proposes a machine learning approach to develop a lightweight security solution to address data altering and man-in-the-middle attacks. The algorithm generates a link fingerprint of the received signal strength indicator (RSSI) value of the communicating IoFT node. The packet is sent to the server unit and it is decoded and matched with the table to identify the path. A trained machine learning model at the server gets the RSSI value from the packet and successfully classify about the presence of an attack. © 2024 IEEE.

关键词： k-nearest neighbors

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Green Information Centric Networking for Future Wireless Communications

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2024年第23期18卷 149-158页

作者： Girirajan, S. Vinoth Kumar, S. Karthick, M. Saju Raj, T. Ponnaian, Geetha Department of Computing Technologies School of Computing SRM Institute of Science and Technology Kattankulathur Tamil Nadu India Department of CSE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Tamil Nadu Chennai India Department of Computer Science and Engineering Nandha College of Technology Tamil Nadu Erode India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Tamil Nadu Chennai India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil Nadu Chennai India

Energy-efficient green information-centric networking (EEGICN) is proposed in this paper for advancing future wireless communication networks by addressing the challenge of energy consumption. This model can adapt the power consumption of network nodes to optimized values according to the associated link utilization. The model aimed to reduce energy consumption and increase network performance and stability. The EEGICN model incorporates efficient routing mechanisms, content caching strategies, and energy-intelligent communication protocols to improve resource utilization across the network infrastructure. EEGICN minimizes large data transmission, reduces power consumption, and reduces network congestion. Popular resources are cached in key network locations, and proximity data is exchanged to achieve this. The model also includes dynamic power management algorithms that adapt to changing traffic demand and network conditions to provide consistent performance across a variety of operational scenarios. In comparison to current wireless network systems that employ various forms of cache, the evaluation findings demonstrated that EEGICN can increase network efficiency by dramatically lowering the number of hops and energy consumption. Future networks may find this application to be a quick and easy way to transmit content. © 2024 by the authors of this article.

关键词： energy efficiency (EE) future wireless communications green information-centric networking information-centric networking (ICN) wireless network

来源：评论

学校读者我要写书评

暂无评论

Collaborative Smart Parking System 3rd

Collaborative Smart Parking System

引用

3rd International Conference on Advanced computing and Intelligent Technologies, ICACIT 2023

作者： Yougesh Raj, S. Velu Prasad, B.A. Vishvakar, S. Hirthik, G. Nair, Prashant R. Department of Computer Science and Engineering Amrita School of Computing Coimbatore Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (纸本)9789819719600

The escalating number of cars on the roads is directly contributing to the exacerbation of traffic congestion, making it increasingly challenging to secure suitable parking spots within cities. Currently, manual labor is primarily responsible for managing the majority of parking spaces in urban areas. However, having the industrial landscape embraces automation to streamline operations and enhance human convenience, the development of intelligent systems has become crucial. This study aims to introduce a collaborative smart parking system that leverages the power of automation. Our goal is to alleviate the laborious process of finding parking spots by designing an Internet of things (IoT)-based collaborative smart parking system that integrates all available parking spaces into a single application. Each parking spot is equipped with an IoT module comprising a proximity sensor to detect the presence of vehicles and a camera to capture and process their number plates. Moreover, our system allows users to reserve parking spots through a cloud-based application. To prevent unauthorized parking in reserved spaces, we employ a camera module and a buzzer. When a vehicle enters a reserved spot, the camera module processes its number plate, and if it identifies the car as unauthorized, both the person who reserved the spot and the central monitoring system receive an alert. While certain cities already have some of these facilities in place, the problem lies in the fragmented nature of the parking spaces. Our solution proposes to consolidate all parking spaces within a single application and harness the efficiency of cloud systems. By offering an application that people can utilize on a daily basis, we aim to simplify their lives and enhance their parking experience. The integration of various parking spaces into a unified platform, combined with the utilization of cloud technology, provides a seamless and efficient solution that individuals can rely on consistently. © The

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Ransome Ware Detection Using Machine Learning and Deep Learning Models 12th

Ransome Ware Detection Using Machine Learning and Deep Learn...

引用

12th International Conference on Recent Trends in computing, ICRTC 2024

作者： Vivek, Vinnakota Sai Lokesh, Vadlamudi Kaushik, Tata Kumaran, U. Umah, B. Devarajan, Gopal Ganesh Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India Department of Computer Science and Engineering SRM Institute of Science and Technology Delhi NCR Campus Uttar Pradesh Ghaziabad India

ISBN: (纸本)9789819789450

This research addresses the critical challenge of ransomware detection through the use of deep learning and machine learning methods. Because ransomware is a serious threat to cybersecurity, it is imperative that advanced techniques be used for prompt detection and mitigation. Using a large dataset, the study concentrates on pertinent features necessary for efficient machine learning model training. The suggested model shows promising results in identifying and averting ransomware attacks by utilizing cutting-edge algorithms. The model’s effectiveness is confirmed by the evaluation metrics (F1 score, recall, accuracy, and precision). By providing a proactive defense against emerging ransomware threats, the findings enhance cybersecurity measures. The study not only provides a strong methodology for ransomware detection but also encourages more research in the area with the goal of continuously bolstering cyber defenses against evolving cyber threats. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

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：