检索结果-内蒙古大学图书馆

Distributed Computing and Optimization Techniques (ICDCOT), International Conference on

作者： Kedar Sawant Rudresh D. Shirwaikar Raj Ravindra Ugavekar Chandrakant Shyam Chodankar Bhupesh Nilkant Tirodkar Ashwek Padolkar Pramesh Gawas Dept. Computer Engineering Agnel Institute of Technology and Design Mapusa India

Fruits are rich in nutrients, vitamins, and minerals and play a crucial role in both dietary health and a nation's economy. In India, diverse fruit cultivation necessitates efficient identification methods. The manual fruit identification processes are time-consuming and biased, leading to agricultural inefficiencies. Hence, the adoption of machine learning and deep learning has gained immense popularity in the automation of the fruit identification preprocess. This study evaluates the performance of DL models, Faster R-CNN and YOLO v8, on a dataset featuring five fruits namely Apple, Cashew Apple, Banana, Mango and Orange for identifying fruits with the comparison between them. While both models yield impressive results, Faster R-CNN generally exhibits higher mAP. However, YOLO v8 excels in precision for specific fruits like Cashew Apple and Banana. The choice between models involves a trade-off between mAP and precision, emphasizing the need for further optimization considering factors like dataset variations, computational performance, and real-world applicability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unleashing the power of federated learning and reinforcement learning in the intelligent evolution of Web3.0 4

Unleashing the power of federated learning and reinforcement...

引用

4th International Conference on Advancement in Electronics and Communication engineering, AECE 2024

作者： Thomas, Aby K Laxmikanth Reddy, C. Kumar Suman, Sanjay Tamilselvi, S. Devarasu, Neelamegam Arulananth, T.S. Alliance University Alliance College of Engineering and Design Dept. of Ece Karnataka Bengaluru India Malla Reddy Engineering College Dept. of Ece Telangana Secunderabad India Dean R&d St. Martin's Engineering College Dept. of Ece Secunderabad India Kongu Engineering College Dept. of Computer Technology TN Erode India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Dept. of Ece TN Chennai India Mlr Institute of Technology Dept. of Ece Telangana Hyderabad India

ISBN: (纸本)9798350364729

Web 3.0's dynamic environment calls for an intelligent transition toward decentralized, privacy-aware, and ethical AI. We have provided a detailed analysis of how the suggested technique, which brings together federated learning and reinforcement learning, stacks up against more conventional approaches to machine learning. We examined these solutions across critical aspects, including data protection, customization, flexibility, ethical compliance, and scalability. The findings have been successfully communicated via the use of visualizations. Our research shows that the suggested approach, which utilizes distributed learning, is superior in many important respects. By putting sensitive data where it belongs - on users' devices - it ensures the highest levels of privacy possible while yet allowing for customization. Reinforcement learning's incorporation guarantees Web 3.0 intelligent systems can adapt to user behavior. In addition, the process is ethically compliant, meeting the requirements of the modern internet age. The capacity to scale up as the number of users increases is also fully supported. While conventional approaches do provide some useful resources, they fall short when compared to the new way. They are less suited to the requirements of Web 3.0 because they typically fail to achieve the optimal balance between data protection, customization, flexibility, and ethical compliance. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

GNN-based Disease Detection and Classification in Cassava Leaf

GNN-based Disease Detection and Classification in Cassava Le...

引用

IoT Based Control Networks and Intelligent Systems (ICICNIS), International Conference on

作者： M Meenalochini A Amalroshini K L Megha Nandhini C R Sogil Murugan Dept. of Computer Science and Design Kongu Engineering College Erode India

ISBN: (数字)9798331518097

ISBN: (纸本)9798331518103

Cassava, a staple crop for millions of people worldwide, is highly susceptible to various leaf diseases, which can significantly reduce crop yields. Detecting and classifying these diseases at an early stage is crucial for effective disease management and crop protection. In this paper, we propose a novel approach for cassava leaf disease classification by combining Convolutional Neural Networks (CNNs) and Graph Neural Networks (GNNs). While CNNs excel at extracting local features from images, they often fail to capture complex spatial relationships between different regions of the leaf. To address this limitation, we integrate GNNs, which are well-suited for learning from irregular, structured data, such as the vein patterns and disease spread structures found in cassava leaves. By modeling the relationship between different regions of the cassava leaf as a graph G (V, E), where V represents nodes corresponding to superpixel regions of the leaf, and E represents edges capturing spatial relationships, the hybrid CNN-GNN model offers a more comprehensive and accurate classification system. The model is trained and evaluated on a dataset of cassava leaf images covering multiple disease categories, demonstrating superior performance over traditional CNN-based image classification techniques. This approach provides a scalable solution for improving the detection and management of cassava leaf diseases.

关键词： Accuracy Scalability Feature extraction Graph neural networks Real-time systems Convolutional neural networks Protection Intelligent systems Diseases Farming

来源：评论

学校读者我要写书评

暂无评论

Security Implementation on IoT using CoAP and Elliptical Curve Cryptography

引用

Procedia computer Science 2023年 230卷 493-502页

作者： Rathnakar Achary Chetan J Shelke Kavin Marx Aishwarya Rajesh Dept. Computer Science and Engineering Alliance College of Engineering and Design Alliance University Bangalore India

IoT devices typically encompass objects or devices equipped with software and internet connectivity, allowing them to collect data. They have limited processing power, memory, and storage. These limitations can make it difficult to secure these devices, as traditional security measures may not be practical. Implementing security for IoT devices can be challenging due to these characteristics, but several steps can be taken to mitigate these challenges. Elliptic Curve Cryptography (ECC) can secure resource constrained IoT devices by providing a more efficient method of encryption and authentication than traditional methods such as RSA. In this paper, we analyzed the lightweight cryptographic algorithm ECC for securing resource-constrained devices such as IoT and evaluated its performance compared to the RSA cryptosystem. The analysis result indicates that ECC is considered to provide stronger security than RSA for the same key length. The CoAP protocol is applied to devices with limited resources, and an examination of its impact is conducted, considering three key performance metrics: CPU usage, bandwidth efficiency, and message communication latency.

关键词： IoT OSCORE CoAP Elliptical Curve Cryptography RSA Resource-constrained devices

来源：评论

学校读者我要写书评

暂无评论

Enhancing Predictive Maintenance with AI: Applications and Impact

Enhancing Predictive Maintenance with AI: Applications and I...

引用

Mobile Computing and Sustainable Informatics (ICMCSI), International Conference on

作者： Chitranjanjit Kaur Anurag Sharma dept. School of Engineering Design and Automation (Computer Science and Engineering) GNA University Phagwara India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

Industrial maintenance is crucial for companies due to its significant impact on operational costs and efficiency. Many industrial firms find that a substantial portion of their expenses stems from equipment breakdowns, failures, or suboptimal performance over time. These costs can sometimes account for up to 50% of overall expenditures. Additionally, companies face various losses, including downtime from breakdowns, challenges in inventory and purchase management, and potential risks of injuries. The objective of this writing is to investigate how Predive maintenance is a footstep towards industry 5.0 where automation of predictive maintenance is evolved to autonomy in maintenance. In addition to it various machine learning algorithms are suggested to identify between healthy and poor data of a machine which is first step in Predictive maintenance then Deep learning algorithms to construct XAI (Explainable artificial Intelligence). Predictive maintenance, production scheduling, problem detection, predictive quality, and increased energy efficiency are highlighted in the typical use cases of the selected AI applications. Data from the real environment is transmitted to be virtually recreated. Efficient industrial maintenance helps mitigate these costs by reducing downtime, improving equipment reliability, and lowering the need for emergency repairs. By implementing a well-designed and optimized maintenance strategy, production plants can ensure their equipment operates as reliably as possible, minimizing disruptions and enhancing overall operational efficiency. Machine Learning (ML) methods have been appeared as a crucial tool in Predictive Maintenance (PdM) applications to prevent failures in equipment that make up the production lines. However, the performance of PdM applications depends on the appropriate choice of the ML method. To save expenses, find inefficiencies, duplicate tool tracking systems, and do other tasks, Digital Twin evaluates material utilization

关键词： Adaptation models Costs Machine learning algorithms Electric breakdown Stacking Companies Writing Vectors Maintenance Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Implementing Secure Key Management and Distribution in Cloud Environment 2

Implementing Secure Key Management and Distribution in Cloud...

引用

2nd IEEE International Conference on Blockchain and Distributed Systems Security, ICBDS 2023

作者： Lamsal, Aman Paul, Aniket Buchade, Amar Nalavade, Jagannath Bidwe, Ranjeet MIT Art Design and Technology University Dept. of Computer Science and Engineering Pune India Vishwakarma Institute of Information Technology Pune Savitribai Phule Pune University Pune India Department of Computer Engineering Pune India

ISBN: (纸本)9798350333763

Key management is considered as an essential aspect of securing cloud-based systems and data. As more organizations move their operations to cloud, the need for secure and efficient key management solutions becomes increasingly important. En-suring security of cloud computing is essential as many users often store their sensitive information with the cloud providers. Cloud service providers offer Key Management Services (KMS) to manage cryptographic keys for their customers, but there are still several challenges related to key management in cloud environments, including key storage, access control, and key rotation. Our research project aims to address these challenges by developing a secure and efficient key management solution for cloud-based systems. We propose a system that uses a combination of various cloud services and encryption algorithms to generate, store, and manage cryptographic keys securely. Our system provides granular access controls, and strong encryption to ensure the confidentiality and integrity of the keys. We believe that our proposed solution will help cloud service providers and organizations to manage their cryptographic keys more efficiently and securely, reducing the risk of unauthorized access and data breaches. This research paper provides a method to effectively manage, store and share the secret key between the parties using the concept of Threshold Cryptography. © 2023 IEEE.

关键词： Access control

来源：评论

学校读者我要写书评

暂无评论

Feature-based Intrusion Detection System with Support Vector Machine 1

Feature-based Intrusion Detection System with Support Vector...

引用

1st IEEE International Conference on Blockchain and Distributed Systems Security, ICBDS 2022

作者： Khodaskar, Manish Medhane, Darshan Ingle, Rajesh Buchade, Amar Khodaskar, Anuja Pune Institute of Computer Technology Dept. of Information Technology Pune India MVPS's K.B.T. College of Engineering Dept. of Computer Engineering Nashik India Dept. of Computer Science & Engineering Naya Raipur India Mit School of Engineering Mit Art Design and Technology University Department of Computer Science & Engineering Pune India Sipna College of Engineering and Technology Dept. of Computer Engineering Amaravati India

ISBN: (数字)9781665428323

ISBN: (纸本)9781665428323

Today billions of people are accessing the internet around the world. There is a need for new technology to provide security against malicious activities that can take preventive/ defensive actions against constantly evolving attacks. A new generation of technology that keeps an eye on such activities and responds intelligently to them is the intrusion detection system employing machine learning. It is difficult for traditional techniques to analyze network generated data due to nature, amount, and speed with which the data is generated. The evolution of advanced cyber threats makes it difficult for existing IDS to perform up to the mark. In addition, managing large volumes of data is beyond the capabilities of computer hardware and software. This data is not only vast in scope, but it is also moving quickly. The system architecture suggested in this study uses SVM to train the model and feature selection based on the information gain ratio measure ranking approach to boost the overall system's efficiency and increase the attack detection rate. This work also addresses the issue of false alarms and trying to reduce them. In the proposed framework, the UNSW-NB15 dataset is used. For analysis, the UNSW-NB15 and NSL-KDD datasets are used. Along with SVM, we have also trained various models using Naive Bayes, ANN, RF, etc. We have compared the result of various models. Also, we can extend these trained models to create an ensemble approach to improve the performance of IDS. © 2022 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

De-Centralized Voting System using Blockchain 1

De-Centralized Voting System using Blockchain

引用

1st IEEE International Conference on Blockchain and Distributed Systems Security, ICBDS 2022

作者： Jangada, Atharva Dadlani, Nimish Raina, Sanchit Sooraj, V.S. Buchade, A.R. Pune Institute of Computer Technology Savitribai Phule Pune University Dept. of Computer Engineering Pune India Mit School of Engineering Mit Art Design and Technology University Dept. of Comp Science and Engineering Pune India

ISBN: (数字)9781665428323

ISBN: (纸本)9781665428323

The revolutionary concept of blockchain, the technology behind the popular cryptocurrency Bitcoin and its successors, has ushered in a new era in the Internet and online services. While most people focus only on cryptocurrencies when they think about Blockchain, in fact many administrative activities and day-to-day services are managed offline and/or privately are now being securely transferred to the Internet as online services. Electronic Voting is one of the trending and important aspect of online services. Traditional voting systems in our country include the use of ballots at polling stations or EVM's (Electronic Voting Machine). The ballot system is prone to tampering, whereas EVM's being a centralised system, are prone to hacking. We aim to offer a more secure, transparent, safer, cheaper and easier to use alternative to the above methods of voting, by making use of the revolutionary Blockchain technology. Smart contracts are meaningful pieces of code that are incorporated into the Blockchain and implemented on schedule at each stage of the Blockchain update. Ethereum and its network is one of the most convenient due to its stability, wide usability and smart contract logic. In this work, we will be implementing and testing a prototype of an E-Voting application using Ethereum Wallet and Solidity language as a smart contract for the Ethereum network. © 2022 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Virtual Field Trip of the Central Heating and Chiller Plant as an Instructional Tool for Thermodynamics Education 53

Virtual Field Trip of the Central Heating and Chiller Plant ...

引用

53rd IEEE ASEE Frontiers in Education International Conference, FIE 2023

作者： Ha, Oai Berrier, Seth Oss, Keif University of Wisconsin-Stout Dept. of Engineering and Technology MenomonieWI United States Dept. of Math Stats and Computer Science University of Wisconsin-Stout MenomonieWI United States University of Wisconsin-Stout Dept. of Design MenomonieWI United States

ISBN: (纸本)9798350336429

This work in progress introduces a framework for developing a virtual tour of the central heating and chiller plant (the Plant) at a university in the US Midwest for teaching and learning Thermodynamics at the campus. Traditionally, this theory-heavy and abstract course is taught using textbooks, lectures, problem solving, and some laboratory experiments. The majority of course content lacks the tangible connections between engineering devices and systems in a close real-world application, making the course challenging and uninteresting for many students. In this project, 360-degree panoramic photos and proper authoring software are employed to render an immersive virtual environment of the Plant that students can visit at any time and from anywhere. The virtual field trip would provide students with tangible insights into thermodynamic and heat transfer processes from over 25 main engineering equipment, devices, and systems at the Plant. Among them are boilers, chillers, a steam turbine, heat exchangers, cooling towers, blowers, and economizers. The follow-up quizzes and assessments are designed to contribute to the course learning outcomes, such as an understanding of phase transitions, thermodynamic properties of steam, and thermal efficiencies of engineering devices. The virtual immersive experiences can help students enhance their learning experiences and engagement in the course's materials without the costs and dangers inherent in a physical tour of the Plant facility. A preliminary result of the virtual tour's evaluation with a group of students and faculty is also included to provide inputs to the next phase of the project. © 2023 IEEE.

关键词： 360-degree panoramic images immersive education mechanical engineering education Thermodynamics education virtual field trip

来源：评论

学校读者我要写书评

暂无评论

Refining Lazy Learners of Machine Learning Algorithms Facing Concept Drift 4

Refining Lazy Learners of Machine Learning Algorithms Facing...

引用

4th International Conference on Emerging Trends in Networks and computer Communications, ETNCC 2024

作者： Sinha, Nidhi Deepika, S. Singh, Paras Nath CMR Institute of Technology Department of Computer Sc. and Engg. Bengaluru560037 India MVJ College of Engineering Dept. of Computer Sc. And Design Bengaluru560067 India GMR institute of Technology Department of Computer Sc. and Engg. Rajam532127 India

ISBN: (纸本)9798350353266

In machine learning, concept drift is the gradual change in the relationship between the input and the target. Typically, this could be an unanticipated shift in the way that input and output data relate to one another over time. Usually, a machine learning model is trained and validated its performance across several metrics. The findings are also satisfactory but something unforeseen and unexpected happened with input and the output prediction has gone crazy. It fails and fells victim to a phenomenon called concept drift. It happens because 'change is the only constant in life.' Concept drift is now discussed as a strong logic to be considered in the accuracy of machine learning algorithms. The required datasets that are currently available for assessing the working of lazy machine learning algorithms. This paper discusses the detection of 'Concept Drift' faced by lazy learners of Machine Learning (ML) algorithms and proposed its solution. Research directions are also examined and discussed. This will immediately benefit researchers in their comprehension of research under the idea of idea of Concept Drift by offering state-of-the-art knowledge. In order to address the shortcomings of lazy ML algorithms such as K-Nearest Neighbor, Logical Weighted Regression, and Radial Base function, a novel heuristic-weight based technique has been employed. XOR (Exclusive OR) is not linearly separable with Radial Base Function which has been implemented to make it linearly separable in Python successfully. © 2024 IEEE.

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：