检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第4期5卷 1613-1623页

作者： Manna, Siladittya Bhattacharya, Saumik Pal, Umapada Indian Statistical Institute Computer Vision and Pattern Recognition Unit Kolkata700108 India Indian Institute of Technology Kharagpur Department of Electronics and Electrical Communication Engineering Kharagpur721302 India

In medical image analysis, the cost of acquiring high-quality data and annotation by experts is a barrier in many medical applications. Most of the techniques used are based on a supervised learning framework and require a large amount of annotated data to achieve satisfactory performance. As an alternative, in this article, we propose a self-supervised learning approach for learning the spatial anatomical representations from the frames of magnetic resonance (MR) video clips for the diagnosis of knee medical conditions. The pretext model learns meaningful context-invariant spatial representations. The downstream task in our article is a class-imbalanced multilabel classification. Different experiments show that the features learned by the pretext model provide competitive performance in the downstream task. Moreover, the efficiency and reliability of the proposed pretext model in learning representations of minority classes without applying any strategy toward imbalance in the dataset can be seen from the results. To the best of our knowledge, this work is the first of its kind in showing the effectiveness and reliability of self-supervised learning algorithms in imbalanced multilabel classification tasks on MR scans. © 2020 IEEE.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive solar power generation forecasting using enhanced neural network with weather modulation

引用

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 10955-10968页

作者： Sujeeth, T. Ramesh, C. Palwe, Sushila Ramu, Gandikota Basha, Shaik Johny Upadhyay, Deepak Chanthirasekaran, K. Sivasankari, K. Rajaram, A. Department of CSE Siddartha Educational Academy Group of Institutions Andhra Pradesh Tirupati India Department of Mechanical Engineering M. Kumarasamy College of Engineering Karur India Department of Computer Engineering and Technology MIT-WPU Maharashtra India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Telangana Hyderabad India Andhra Pradesh Mylavaram India Department of Computer Science and Engineering Graphic Era hill univeristy Dehradun India Department of Electronics and Communication Engineering Saveetha Engineering College Chennai India Department of Electronics and Communication Engineering Akshaya College of Engineering and Technology Coimbatore India Department of Electronics and Communication Engineering E.G.S. Pillay Engineering College Nagapattinam India

Solar power generation forecasting plays a vital role in optimizing grid management and stability, particularly in renewable energy-integrated power systems. This research paper presents a comprehensive study on solar power generation forecasting, evaluating traditional and advanced machine learning methods, including ARIMA, Exponential Smoothing, Support Vector Regression, Random Forest, Gradient Boosting, and Physics-based Models. Moreover, we propose an innovative Enhanced Artificial Neural Network (ANN) model, which incorporates Weather Modulation and Leveraging Prior Forecasts to enhance prediction accuracy. The proposed model is evaluated using real-world solar power generation data, and the results demonstrate its superior performance compared to traditional methods and other machine learning approaches. The Enhanced ANN model achieves an impressive Root Mean Square Error (RMSE) of 0.116 and a Mean Absolute Percentage Error (MAPE) of 36.26%. The integration of Weather Modulation allows the model to adapt to changing weather conditions, ensuring reliable forecasts even during adverse scenarios. Leveraging Prior Forecasts enables the model to capture short-term trends, reducing forecasting errors arising from abrupt weather changes. The proposed Enhanced ANN model showcases its potential as a promising tool for precise and reliable solar power generation forecasting, contributing to the efficient integration of solar energy into the power grid and advancing sustainable energy practices. © 2024 – IOS Press.

关键词： Solar power generation

来源：评论

学校读者我要写书评

暂无评论

BiFrost: A Blockchain-Based Decentralized Messaging Application

BiFrost: A Blockchain-Based Decentralized Messaging Applicat...

引用

International Conference on Data Science and Network engineering, ICDSNE 2023

作者： Pandey, Himanshu Siraswal, Akhil Kaushik, Ekta Pandey, Dilkeshwar Kapoor, Sparsh Pahuja, Hunny Department of Computer Science and Engineering KIET Group of Institutions Delhi NCR Ghaziabad India Department of Electronics and Communication Engineering KIET Group of Institutions Delhi NCR Ghaziabad India

ISBN: (纸本)9789819967544

BiFrost is a revolutionary solution for secure online communication and data storage. It addresses security concerns such as eavesdropping, man-in-themiddle attacks, and censorship by offering decentralization, immutability, and data security through the use of blockchain technology. User-submitted data are added directly to the blockchain, creating a global copy in each node, and only authorized users can access the data using private keys. The system is fully decentralized, meaning there is no central authority, making it immune to censorship and government oppression. The technology used in BiFrost includes IPFS, smart contracts, Ethereum, INFURA, Solidity, and SPF. BiFrost provides a secure and decentralized solution for online communication and data storage, eliminating the need for a trusted intermediary and ensuring the privacy and security of data. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

A review on analysis and prediction methodologies of crop yield pattern 5th

A review on analysis and prediction methodologies of crop yi...

引用

5th International Conference on Advances in AI for Biomedical Instrumentation, electronics and Computing, ICABEC 2023

作者： Neha Ahlawat, Anil Chaudhary, Himanshu Department of Computer Science Engineering KIET Group of Institutions Delhi NCR Ghaziabad India Department of Electronics and Communication Engineering KIET Group of Institutions Delhi NCR Ghaziabad India

ISBN: (纸本)9781032642987

Making supportive decisions for crop production, such as crop name recommendations and forecasts for crop production, requires machine learning implementation. Numerous machine learning classifiers and algorithms are employed in this. Climatic factors (temperature, rainfall, precipitation, sun radiation, and humidity), edaphic factors (pH, kind, and proportions of nitrogen, phosphorus, and potassium in the soil), and physiographic factors (altitude, steepness of slope, exposure to light, and wind) are some of the variables or factors that influence crop production. However, the most common variables are temperature, soil pH, precipitation, and humidity, and the most common algorithms are Examples of artificial neural networks and deep learning algorithms include Random Forest, Support Vector Machine, Linear Regression, Long Short-Term Memory, Convolution Neural Network, and Deep Neural Network. As part of this study, we reviewed the literature to ascertain the techniques and influencing factors that have been used in agricultural output prediction. © 2024 The Author(s).

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Smart Helmet and Bike Tracking System

Smart Helmet and Bike Tracking System

引用

2023 International Conference on Power, Instrumentation, Energy and Control, PIECON 2023

作者： Smriti Tiwari, Vikas Srivastava, Richa Sharma, Ms. Swati KIET Group of Institutions Department of Electronics and Communication Engineering Ghaziabad India KIET Group of Institutions Department of Computer Science and Engineering Ghaziabad India

ISBN: (纸本)9798350399769

India is a country that is going to become the most populated country in the world in the coming years. It has a large population of youth. Today's youth enjoy riding bikes and often disregard safety precautions such as wearing a helmet. Because of these, two-wheelers accidents are increasing day by day, which causes deaths and several types of serious injuries. Significant causes of death are head injuries, which can be prevented by wearing a helmet and taking proper safety precautions. One can also see that drinking and driving have also increased, leading to road accidents. Overspeeding is also one of the major factors. The increasing rate of road accidents made us develop a smart helmet using the internet of things, which reduces accidents and the risk of death. It has a feature where the bike starts only if the rider wears a helmet. If the rider is over-drunk or not wearing the helmet, the ignition will automatically switch off. If any accident occurs, the GSM modem and the GPS modem will send the message to the registered contact number by using a SIM card. In addition, if the bike or helmet is stolen, the owner can easily find out the exact location of the bike and the helmet using this device. This feature is necessary for a country like India, where bike theft cases are frequent and high. © 2023 IEEE.

关键词： Microcontrollers

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence and Li-Fi for Autonomous Vehicles and Future Transportation Systems 5

Artificial Intelligence and Li-Fi for Autonomous Vehicles an...

引用

5th International Conference on Data Intelligence and Cognitive Informatics, ICDICI 2024

作者： Mishra, Sandeep Pandey, Bipin Kumar, Rajat Shukla, Kaustubh Kumar Dronacharya Group of Institutions Department of Computer Science Engineering Uttar Pradesh Greater Noida India Dronacharya Group of Institutions Department of Electronics and Communication Engineering Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350389609

One of the major challenging task is to maintain the Autonomous vehicles as well as to analyze the future transportation systems. To solve such kind of issues proposed three different technologies, Artificial Intelligence, Light Fidelity and LoRa has been analyzed. AI and LiFi technologies have the potential to revolutionize transportation systems, especially for autonomous vehicles. LiFi uses visible light for data transmission, offering higher rates, security, and energy efficiency. AI is crucial for autonomous vehicles, enabling real-time data transmission, secure communication, intelligent traffic management, and cooperative driving. Challenges include cost, range limitations, and infrastructure integration. The research proposes an innovative system combining LiFi as well as LoRa technologies to improve navigation in congested urban environments. The LiFi transmitter uses visible light to transmit location information to LiFi receivers in vehicles, providing continuous, seamless navigation even in areas without service. The system also broadcasts vehicle location to the outside world via a LoRa module, providing long-range and low-power navigation in non-serviceable locations like terrines, valleys, and tunnels. AI, LiFi, and LoRa are crucial technologies for autonomous vehicles and transportation systems. AI provides the "brain"for autonomous vehicles, while LiFi offers high-speed, secure, and interference-free communication. LoRa is ideal for long-range, low-data-rate communication, enabling accurate decision-making, enhanced safety, and efficient transportation. These technologies are essential for a future autonomous vehicle-friendly future. © 2024 IEEE.

关键词： Light transmission

来源：评论

学校读者我要写书评

暂无评论

AI-based Learning Techniques for Bladder Cancer Detection

AI-based Learning Techniques for Bladder Cancer Detection

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Kumar, Sandeep Saurabh Aggarwal, Ankita Aryan Institute of Technology Ghaziabad India Chandigarh Group of Colleges Chandigarh College of Engineering Department of Computer Science & Engineering Mohali India Chandigarh Group of Colleges Chandigarh Engineering College Department of Electronics & Communication Engineering Mohali India

ISBN: (纸本)9798331508685

There is no doubt that the main issue to address in these patients is the early diagnosis of Bladder carcinoma. This work aims at initiating a new path in this research and undertakes advanced artificial intelligence (AI) and machine learning to enhance bladder cancer diagnosis. Bladder cancer is one of the more widespread malignant neoplasms, it is more prevalent in the male population and particularly in male gerontocracy. Conventional diagnostic approaches are hypertrophied and crippled by constraints that lead to diagnostic imperfections and unkind lateness. There stands a great opportunity to deal with these challenges through the implementation of Artificial Intelligence in healthcare. By incorporating the modern artificial intelligence models such as CNN and RNN along with other modern techniques, this research intends to improve the diagnostic outcomes and provide strong prognosis. It is through a comprehensive method of data preprocessing and feature engineering, an incorporation of ethical factors, and the use of complex algorithms that this research hopes to advance the future of precision medicine. In this context, the customized solutions based on the most effective data also expand the scope of the diagnosis of bladder cancer and bring positive changes to the treatment of patients. © 2025 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

A Detailed Analysis of Cloud Storage and Key Management Techniques in IoT Driven Smart Grids 7

A Detailed Analysis of Cloud Storage and Key Management Tech...

引用

7th International Conference on Circuit Power and Computing Technologies, ICCPCT 2024

作者： Sivaprasad Manivannan, I. Roobert, A. Andrew Muthukumaran, N. Rohini College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu India Francis Xavier Engineering College Department of Electronics and Communication Engineering Tirunelveli627003 India Sri Eshwar College of Engineering Centre for Computational Imaging and Machine Vision Department of Electronics and Communication Engineering Tamil Nadu Coimbatore641202 India

ISBN: (纸本)9798350372816

The Internet of Things (IoT) technology has revolutionized smart grid settings, enhancing efficiency and enabling advanced data analytics. However, the integration of IoT devices within smart grids introduces significant challenges related to data storage and security. This survey provides a comprehensive review of the various classifiers and optimization algorithms employed to enhance cloud storage solutions and key management systems within smart grid environments. Moreover, it symmetrically examines different classifiers, like Machine Learning (ML) and Deep Learning (DL) methods, which are designed for managing cryptographic keys, focusing on their ability to secure communications, authenticate devices, and ensure data integrity in the presence of cyber threats. Additionally, it categorizes and evaluates a wide range of optimization methods, including evolutionary algorithms, particle swarm optimization (PSO), gray wolf optimization (GWO) and firefly algorithm (FFA) based techniques for optimizing the classifiers, highlighting their applicability in optimizing storage capacities, data retrieval speeds, and cost-effectiveness. By synthesizing recent advancements and comparing the efficacy of these techniques, the survey identifies the best individuals and emerging trends that promise to strengthen the resilience and efficiency of IoT-enabled smart grids. The findings promote the critical role of integrated classifiers and optimization techniques in achieving scalable, secure, and reliable smart grid infrastructures. © 2024 IEEE.

关键词： Data integrity

来源：评论

学校读者我要写书评

暂无评论

A Novel Hybrid, BERT and Deep Learning Model Network Intrusion Detection System for Healthcare electronics

引用

IEEE Transactions on Consumer electronics 2024年第1期71卷 1-1页

作者： Alferaidi, Ali Yadav, Kusum Alharbi, Yasser Alreshidi, Eissa Jaber Alreshidi, Abdulrahman Aboshosha, Bassam W. Sharma, Rohit Alkhayyat, Ahmed Aray, Daniel Gavilanes College of Computer Science and Engineering University of Ha’il Ha’il Saudi Arabia Department of Communication and Computer Engineering Higher Institute of Engineering El-Shorouk Academy El-Shorouk City Egypt Department of Electronics and Communication Engineering ABES Engineering College Ghaziabad Uttar Pradesh India Ahmed Alkhayyat College of technical engineering The Islamic University Najaf Iraq Engineering Research and Innovation Group Universidad Europea del Atlántico Santander Spain

IoMT has become an attractive playground for cybercriminals due to its market value and rapid growth. As the amount of sensitive data transmitted across IT infrastructures grows, healthcare organizations and companies that generate wearable data become targets for attackers. Recently, government agencies and healthcare organizations have prioritized collecting this data and using machine learning to protect users’ privacy. In all test cases, the proposed method performed better than any other method, including the IoMT intrusion dataset, with an accuracy increase of 2.9%. It can also monitor IoMT networks within the healthcare and medical environment to protect IoMT devices and networks from attackers. Based on the ECU-IoHT dataset, it achieves 99% performance improvement in accuracy, precision, recall, and F1-score compared with existing anomaly detection models. The proposed model shows higher detection accuracy than the existing latest state-of-arts. IEEE

关键词： Wearable technology

来源：评论

学校读者我要写书评

暂无评论

MARM-HyLiWi: Mobility-Aware Rate Maximization in Link Aggregation Enabled Hybrid Li-Fi/Wi-Fi Networks 17

MARM-HyLiWi: Mobility-Aware Rate Maximization in Link Aggreg...

引用

17th International Conference on communication Systems and NETworkS, COMSNETS 2025

作者： Paramita, Saswati Mondal, Rajorshi Bhattacharya, Arani Bohara, Vivek Ashok Srivastava, Anand Delhi Wirocomm Research Group Center of Excellence Li-Fi Department of Electronics and Communication Engineering New Delhi India IIIT Delhi Department of Computer Science and Engineering New Delhi India

ISBN: (纸本)9798331531195

Light Fidelity (Li-Fi) offers high data rates in confined areas but is limited by susceptibility to signal blockages and constrained coverage. To address these limitations, Li-Fi is often integrated with Wi-Fi in a heterogeneous network (HetNet), leveraging Li-Fi's speed with Wi-Fi's broader coverage. However, hybrid networks introduce frequent handovers between Li-Fi and Wi-Fi access points (APs), especially for users near blind spots or with limited mobility. This paper proposes a link aggregation (LA) approach for a Li-Fi and Wi-Fi HetNet (LA-HLWN), where users receive data from both types of APs simultaneously, enhancing data rates and reducing handover frequency. To manage network load effectively, we develop an algorithm for dynamic data rate allocation, formulated as a multi-dimensional commodity flow problem that considers factors such as user requirements, AP signal quality, and backhaul conditions. Given the NP-hard nature of this problem, our solution models it initially as an integer linear programming (ILP) challenge and then applies a relaxed linear programming (LPP) approach with a rounding technique for real-time allocation. Additionally, to balance throughput and reduce the computational overhead, we implement a strategy to control handover frequency and load distribution across APs, achieving a 54% improvement in throughput. This approach demonstrates the potential of LA in enhancing user satisfaction and system performance in hybrid Li-Fi/Wi-Fi networks. © 2025 IEEE.

关键词： Wireless local area networks (WLAN)

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：