检索结果-内蒙古大学图书馆

2nd International Conference on Emerging Trends in Information Technology and engineering, ic-ETITE 2024

作者： Bhuvaneswari, S. Thomas, Joel Nithish, S. Prithvi, S. Easwari Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350328202

Brain tumor diagnosis is a critical task in the field of medical imaging, with the potential to significantly impact patient outcomes and treatment planning. The use of deep learning has been more well-known within the last ten years as a potential method for improving and automating the detection and categorization of brain tumors. The goal of this literature review is to present a thorough overview of the application of deep learning to the diagnosis of brain tumors. © 2024 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

A Survey on Tea Plant Disease Prediction for Blister Blight 2

A Survey on Tea Plant Disease Prediction for Blister Blight

引用

2nd International Conference on Emerging Trends in Information Technology and engineering, ic-ETITE 2024

作者： Gowthami, M. Nila Baaradhy, I. Nithin, V. Subhash, J. Easwari Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350328202

This survey seeks to give a general overview of the current state of Tea Plant disease prediction for the Blister Blight disease. To construct this system, IoT and machine learning approaches are applied. The goal of the research is to improve sustainable farming methods through early detection and prevention. The climatic conditions of the farmlands are analysed with a set of sensors. Real time input from the IoT setup is processed by the Machine Learning algorithms for detection of the Blister Blight disease. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Mathematical and Dynamical Model for Analyzing H-Shaped PM Vernier Motor for Electric Motorcycle Mid-Drive Applications

引用

IEEE Transactions on Energy Conversion 2025年第1期40卷 529-543页

作者： Ghods, Mehrage Faiz, Jawad Bazrafshan, Mohammad Amin Gorginpour, Hamed Toulabi, Mohammad Sedigh University of Tehran School of Electrical and Computer Engineering College of Engineering Tehran*** Iran Persian Gulf University Department of Intelligent Systems Engineering and Data Science Bushehr*** Iran Oakland University Department of Electrical and Computer Engineering RochesterMI48309 United States

The permanent magnet (PM) Vernier machines enhance torque density and decrease cogging torque compared to conventional permanent magnet synchronous motor. This paper presents a novel fractional-slot H-shaped PM Vernier machines, which incorporates unique design for the PM housing and rotor core construction. These designs are specifically optimized for the small-scale electric vehicles application. The choice of the PM arrangement is based on the combination of V-shaped and spoke-array PM topologies. The aim is to achieve a higher torque density than V-shaped PM machines, while reducing cogging torque compared to spoke-array PM machines. By using this methodology, leakage fluxes in the terminal region of the PMs reduce, resulting in an augmentation of both flux-linkage and power factor. A prototype 680 W motor was fabricated with 12 slots and 8 poles to verify the accuracy and effectiveness of the proposed model. Mathematical model and dynamical analysis are proposed for the analytical prediction of machine performance. Due to the unique shape feature of the machine, the conformal mapping approach is applied to design the rotor core. To validate the model, the predicted performance of the motor was compared with those obtained by finite element analysis and experiments. © 1986-2012 IEEE.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

AI Techniques for Anomaly Detection in Video Surveillance Using Deep Learning Method 3

AI Techniques for Anomaly Detection in Video Surveillance Us...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Jain, Swati Choudhary, Naveen College of Technology and Engineering Department of Computer Science and Engineering Udaipur India

ISBN: (纸本)9798350372120

Researchers are becoming more interested in the topic of anomaly detection in video surveillance, which has made substantial advancements. In many domains, including industrial safety, surveillance, and healthcare monitoring, video anomaly detection is essential. This work suggests a novel approach for applying deep learning algorithms to identify abnormalities in films. The complexity and variety of real-world data sometimes pose challenges for traditional approaches, which results in a lack of accuracy and resilience. Deep learning methods, on the other hand, have demonstrated incredible promise in identifying spatiotemporal patterns in video data. This research investigates and identifies outliers in video surveillance by examining different kinds of video *** application scenario, which depends on the types of data and anomalous types of behavior with different circumstances, is the emphasis of the various methodologies. Large datasets are used to train the Convolutional Neural Network architecture, which enhances its capacity to learn general visual representations. Our work gives futuristic performance in terms of efficiency and accuracy as demonstrated by the experimental findings. © 2024 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

The Agro Predictor - A Smart farming approach using Deep Learning

The Agro Predictor - A Smart farming approach using Deep Lea...

引用

2024 International Conference on Recent Innovation in Smart and Sustainable Technology, ICRISST 2024

作者： Sheela, K. Santha Threegha, S. Yazhmozhe, G.M. Velammal College of Engineering and Technology Computer Science Engineering Madurai India

ISBN: (纸本)9798350309140

The prime focus of this Agro-Predictor system which relies on the key learnings of the Internet of Things and Deep Learning Approach, to benefit the agricultural sector, placing its undivided attention on critical areas. Analysis of soil types and different weather conditions affecting, recommendations based on all the predictions made for the best production and farming. The integration of advanced technologies like Deep Learning, Data Mining, IOT and etc, has influenced agricultural sector transformation in various ways. The potential of deep learning models has been demonstrated to revolutionize farming practices by collecting the required data set, training and segregating the following, and predicting the required outcomes with the best recommendations. The work highlights the need for innovative solutions to address the growing global demand by identifying problem areas that require further research for sustainable agriculture by predicting various factors to reach the required solutions in farming. © 2024 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Two-Tier Hybrid Cryptographic Models for Secure Data Transactions in Cloud Computing 2

Performance Evaluation of Two-Tier Hybrid Cryptographic Mode...

引用

2nd IEEE International Conference on Contemporary Computing and Communications, InC4 2024

作者： Debnath, Pankoj Kar, Tonoy Chandra Ashraf, Din Md Arif, Redwanul Islam Lysuzzaman, Md Sylhet Engineering College Department of Computer Science and Engineering Sylhet Bangladesh

ISBN: (纸本)9798350383652

Cloud computing is a trending and enormous technology. With the improvements in the field of Cloud computing, the main challenge arises in the transaction of data securely from one platform to another. Various cryptographic algorithms are used to provide a secure transaction of data. However, conventional cryptographic algorithms might not be sufficient enough for modern threats. To face these potential vulnerabilities, hybrid cryptographic algorithms can be the solution. Hybrid cryptography integrates multiple cryptographic algorithms to enhance performance and overall safety. RSA(Rivest-Shamir-Adleman) is the most common public key algorithm for encryption and decryption. This paper analyzes a modified form of RSA known as Modified-RSA that enhances security in hybrid cryptographic algorithms by incorporating three prime numbers instead of two. The Modified-RSA(MRSA) hybrid models are compared with the original RSA hybrid models with some theoretical and practical aspects. In this research, a comparative study of two-tier hybrid cryptographic models applied to secure data on the cloud is presented. Practical implementations were conducted with hybrid models of RSA and Modified-RSA using Python simulation. Encryption time, decryption time, average throughput, and efficiency were found using relatively more extensive data. The main motive was to find out the performance of every cryptographic hybrid and see which hybrid model is more efficient. © 2024 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Taylor jellyfish search algorithm enabled feature selection and deep learning for big data classification using mapreduce framework

引用

Australian Journal of Electrical and Electronics engineering 2024年第2期21卷 178-192页

作者： Kalpana, K. Sunil Vijaya Kumar, G. Madhavi, K. Research Scholar Department of Computer Science and Engineering JNTUA College of Engineering Andhra Pradesh India Nandyal Telangana India Department of CSE JNTUA College of Engineering JNTUA Ananthapuramu Andhra Pradesh India

Nowadays, the increasing growth of technology contributes various organisations to storing a huge amount of records using web servers in the form of big data. The big database possesses a vast amount of relevant and irrelevant features, and the less significant features are difficult to remove which makes the process time-consuming and more complex. Hence, this paper proposes an optimisation algorithm, named the Taylor Jellyfish Search Optimisation (TaylorJSO) for selecting the relevant features. Here, an optimisation-based deep learning approach called Taylor Jellyfish Search Optimisation-Deep Maxout Network (TaylorJSO-DMN) is introduced to classify big data more effectively by selecting optimal features. In this model, the input database is preprocessed using quantile normalisation and uses the oversampling of imbalanced classes for data augmentation. In the MapReduce framework, the selection of optimal features is performed in the mapper phase, whereas in the reducer phase, the DMN is used for the classification of big data. The DMN is trained using the introduced TaylorJSO algorithm to improve the classification performance of big data classification. Moreover, the TaylorJSO-DMN model attained greater performance with a maximum of 92.5% accuracy, 91.6% sensitivity, and 92.9% specificity than other traditional approaches. ©, Engineers Australia.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Integration of Cross-Chain Technology-Based High-Performance Blockchain Network for Industrial Internet of Things 4

Integration of Cross-Chain Technology-Based High-Performance...

引用

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

作者： Kothari, Rakshit Jain, Kalpana Choudhary, Naveen College of Technology and Engineering MPUAT Computer Science and Engineering Udaipur India

ISBN: (纸本)9798350353266

The Internet of Things (IoT) has emerged as a promising technology for connecting physical objects and enabling communication between them. However, IoT faces several challenges such as security, privacy, and interoperability that need to be addressed before large-scale deployment. Blockchain has the potential to address these challenges due to its decentralized architecture, cryptographic security, immutability and consensus mechanisms. This paper explores the integration of blockchain technology with IoT for industrial applications. A cross-chain architecture is proposed to build a high-performance blockchain network customized for the needs of Industrial IoT (IIoT). The limitations of existing blockchain platforms like low transaction throughput are overcome by improvements in the consensus algorithm and employing a multi-chain structure. A proof-of-stake based consensus is implemented to achieve fast consensus and improve scalability. Cross-chain communication protocols are designed to enable interoperability between heterogeneous blockchains. The experimental evaluation demonstrates that the resulting blockchain network can achieve over 1000 transactions per second throughput per chain while maintaining decentralization, security and low latency. The cross-chain structure enables this performance to scale as the network expands. The paper provides comprehensive technical details of the various components of the blockchain platform including consensus, cross-chain communication and network structure. The designed blockchain architecture can potentially enable several IIoT use cases by enhancing security, accessibility, automation and coordination of industrial systems. © 2024 IEEE.

关键词： Blockchain Network Cross-Chain Technology Industrial Internet of Things Practical Byzantine Fault Tolerance Proof-of-Work (PoW) Proof-ofStake

来源：评论

学校读者我要写书评

暂无评论

NariNavi-Women and Public Transportation Safety 1

NariNavi-Women and Public Transportation Safety

引用

1st International Conference on Computational Intelligence for Security, Communication and Sustainable Development, CISCSD 2024

作者： Ganesan, Srividhya Nirmala, M. Mohana, P. Reddy, Pandirla Somanatha Monish, P. New Horizon College of Engineering Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350365405

This study proposes a rigorous strategy for addressing women's safety on public transit networks, leveraging advanced machine learning methodologies to create a secure and welcoming environment for all passengers. The approach integrates predictive policing algorithms, including Random Forests and Decision Trees, to analyze historical data and identify patterns associated with harassment incidents, enabling strategic resource allocation. Real-time monitoring is facilitated by anomaly detection algorithms such as isolation Forests, which recognize aberrant patterns indicative of potential threats. Natural language processing (NLP) techniques, particularly sentiment analysis, extract valuable insights from diverse data sources, informing targeted interventions on routes were passengers report feelings of insecurity. filtering and geospatial algorithms contribute to recommendation systems and precise location tracking through mobile panic buttons. Recurrent neural networks (RNNs) and Long Short-Term Memory (LSTM) models analyze evolving behavior in crowded spaces. This comprehensive framework is underpinned by machine learning classifiers, ensuring real-time data processing and alert generation, while an emphasis on ethical considerations and privacy safeguards aligns the strategy with regulatory standards and user expectations. Ultimately, the integration of these technologies aims to transform the public transit experience, fostering an elevated sense of security for all passengers, particularly women, as they navigate their journeys. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Ocean Wings-Human Identification Using Drone for Sea Rescue Operations

Ocean Wings-Human Identification Using Drone for Sea Rescue ...

引用

2024 International Conference on E-Mobility, Power Control and Smart Systems, ICEMPS 2024

作者： Sruthy, K.G. Sulthana Rinsy, A.P. Hafiyya, R.M. Hanan, M. Gokul Dev, K. Anand, Jithamanue Fairooz Muhammed, M. Mea Engineering College Computer Science Engineering Kerala Malappuram India

ISBN: (纸本)9798350394399

This study explores the application of YOLOv8, a state-of-the-art object detection algorithm, for human detection in open water using drones in Search and Rescue (SAR) operations. Open water environments present unique challenges for human detection due to dynamic conditions, limited visibility, and the vastness of the area. Drones equipped with SAR sensors and YOLOv8 offer a promising solution to enhance the efficiency and effectiveness of search and rescue missions. The research involves the development of a specialized model based on YOLOv8 architecture, fine-tuned for human detection in open water scenarios. A dataset comprising diverse open water images is used for training and validation, ensuring the robustness of the model across various conditions. The drone's capabilities, including real-time data transmission and high maneuverability, are leveraged to conduct simulated SAR missions in open water environments. © 2024 IEEE.

关键词： Drones

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：