检索结果-内蒙古大学图书馆

Path Loss Modeling: A Machine Learning Based Approach Using Support Vector Regression and Radial Basis Function Models

引用

Open Journal of Applied sciences 2022年第6期12卷 990-1010页

作者： Stephen Ojo Arif Sari Taiwo P. Ojo College of Engineering Anderson University Anderson SC USA Department of Management Information Systems Girne American University Girne Cyprus Computer Science Department Florida A&M University Tallahassee FL USA

Path loss prediction models are vital for accurate signal propagation in wireless channels. Empirical and deterministic models used in path loss predictions have not produced optimal results. In this paper, we introduced machine learning algorithms to path loss predictions because it offers a flexible network architecture and extensive data can be used. We introduced support vector regression (SVR) and radial basis function (RBF) models to path loss predictions in the investigated environments. The SVR model was able to process several input parameters without introducing complexity to the network architecture. The RBF on its part provides a good function approximation. Hyperparameter tuning of the machine learning models was carried out in order to achieve optimal results. The performances of the SVR and RBF models were compared and result validated using the root-mean squared error (RMSE). The two machine learning algorithms were also compared with the Cost-231, SUI, Egli, Freespace, Cost-231 W-I models. The analytical models overpredicted path loss. Overall, the machine learning models predicted path loss with greater accuracy than the empirical models. The SVR model performed best across all the indices with RMSE values of 1.378 dB, 1.4523 dB, 2.1568 dB in rural, suburban and urban settings respectively and should therefore be adopted for signal propagation in the investigated environments and beyond.

关键词： Support Vector Regression Radial Basis Function Machine Learning Path Loss Empirical Deterministic

来源：评论

学校读者我要写书评

暂无评论

A Cloud-Based UV Monitoring System for Remote Real-Time UV Exposure Tracking 4

A Cloud-Based UV Monitoring System for Remote Real-Time UV E...

引用

4th International Conference on Smart Electronics and Communication, ICOSEC 2023

作者： Dankan Gowda, V. Prasad, V. Nuthan Prasad, K.D.V. Prasad, V.K. Satya Mahajan, Yogesh Suneetha, Sampathirao Bms Institute of Technology and Management Department of Electronics and Communication Engineering Karnataka Bangalore India M S R i T Department of Electronics and Communication Engineering Karnataka Bangalore India Symbiosis Institute of Business Management Hyderabad India Pune India Symbiosis International University Symbiosis Centre for Management and Human Resource Development Maharashtra Pune India Andhra University College of Engineering Andhra University Department of Computer Science and Systems Engineering Andhra Pradesh Visakhapatnam India

ISBN: (纸本)9798350300888

Due to the widespread nature of sun-related health risks, sophisticated UV monitoring systems are urgently needed. This research study introduces a cloud-based UV monitoring system with the intent of remotely tracking and analyzing UV exposure in real time. The system incorporates a network of UV sensors deployed in various locations, continuously collecting UV radiation data. These sensors are linked to a cloud system, which allows for easy sharing and processing of collected data. As a result, we're working to perfect a cutting-edge device that can monitor vitamin D absorption, measure cumulative UV exposure, and warn of impending danger. Extensive studies have demonstrated the benefits of UV exposure for both general health and protection against the newly discovered coronavirus. However, finding a happy medium is important because too much sun exposure can cause cancer, lupus flares, and cataracts. The proposed model gives users the ability to set their own daily UV exposure limits, taking into account clinically validated thresholds for various skin tones. The developed sensor module is able to measure the UV index with high precision even in bright sunlight because it closely mimics the skin erythema spectrum. © 2023 IEEE.

关键词： Ultraviolet radiation

来源：评论

学校读者我要写书评

暂无评论

Steps Towards Satisficing Distributed Dynamic Team Trust

arXiv

引用

arXiv 2023年

作者： Hunt, Edmund R. Baber, Chris Sobhani, Mehdi Milivojevic, Sanja Yusuf, Sagir Musolesi, Mirco Waterson, Patrick Maynard, Sally School of Engineering Mathematics and Technology University of Bristol United Kingdom School of Computer Science University of Birmingham United Kingdom Bristol Digital Futures Institute University of Bristol United Kingdom Department of Computer Science University College London United Kingdom Human Factors and Complex Systems Group Loughborough University United Kingdom

Defining and measuring trust in dynamic, multiagent teams is important in a range of contexts, particularly in defense and security domains. Team members should be trusted to work towards agreed goals and in accordance with shared values. In this paper, our concern is with the definition of goals and values such that it is possible to define ‘trust’ in a way that is interpretable, and hence usable, by both humans and robots. We argue that the outcome of team activity can be considered in terms of ‘goal’, ‘individual/team values’, and ‘legal principles’. We question whether alignment is possible at the level of ‘individual/team values’, or only at the ‘goal’ and ‘legal principles’ levels. We argue for a set of metrics to define trust in human-robot teams that are interpretable by human or robot team members, and consider an experiment that could demonstrate the notion of ‘satisficing trust’ over the course of a simulated mission. © 2023, CC BY.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Smart college automation using IoT

引用

AIP Conference Proceedings 2024年第1期3075卷

作者： B. Bhuvaneswaran K. Vijay D. Sorna Shanthi A. Charann Department of Computer Science and Engineering Rajalakshmi Engineering College Chennai India Department of Computer Science and Business Systems Rajalakshmi Engineering College Chennai India

In this era of internet, we aspire to control everything through the internet. Internet of Things known as IoT has been a buzz word in the industry for quite a long time. IoT aims at controlling devices and transmitting data through the internet, which helps in efficient utilization of resources and minimize the human effort. Many sensor and control nodes are linked to a central cloud server and managed by a single administrator who serves as a go-between for the many users. While the administrator has access to and control over all nodes connected to each user, each individual user only has access to and control over their own connected nodes. Every aspect of your home’s electronics can be managed from your smartphone or computer, no matter where you are, thanks to the IoT infrastructure being put in place. Using IoT for controlling the electrical parts of a building could be proved energy efficient. Especially in colleges where there are lots of classrooms and blocks, it would be difficult for people to manually go and check everyday after the classes are over, to ensure that the electrical devices in classrooms are switched off. Also, in air-conditioned places, after reaching the required temperature or in winter seasons, according to the need, the air conditioner can be cut off. This application helps in monitoring and controlling all electronic devices through cloud and also to set automatic cut off for rooms where there is air conditioning, using the ESP8266 module. Also, we use a mechanism to detect if there are any people in the room, if not we will turn off the lights and fans in that room.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advancements in Artificial Intelligence for Better Image Analysis, Recognition, and Interpretation in the Field of Image Processing

Advancements in Artificial Intelligence for Better Image Ana...

引用

Communications and Information Technologies (GCCIT), Global Conference on

作者： V. Saravanan A. Adaikkammai G. Sasikala Iyswariya A A. Babisha M. Latha Department of Nano Electronics Materials and Sensors Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamilnadu India Department of Computer Science and Business Systems R.M.D. Engineering College Department of ECE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Department of ECE R.M.K. Engineering College Chennai Department of Artificial Intelligence and Data Science Panimalar Engineering College Department of IT SRM Institute of Science and Technology

ISBN: (数字)9798350388916

ISBN: (纸本)9798350388923

The rapid advancement of artificial intelligence (AI) has brought about a significant revolution in image processing. This revolutionary technology has enabled the analysis, recognition, and interpretation of images in ways that were previously inconceivable. An investigation into the most recent developments in artificial intelligence techniques that have improved the efficiency and precision of image processing tasks is presented in this study. We survey the emergence of transformer architectures and the integration of deep learning models, namely Convolutional Neural Networks (CNNs), to explore how these technologies have transformed the understanding and application of images in several industries. An overview of existing image processing methods and the limits of those approaches is presented at the beginning of our research. This highlights the necessity of more advanced AI-driven solutions. After that, we examine the advancements that have been made in artificial intelligence, such as the incorporation of attention processes, the development of more effective CNN architectures, and the utilisation of generative adversarial networks (GANs) for the purpose of picture synthesis and augmentation. The purpose of this research is to investigate the impact that artificial intelligence has on particular applications of image processing, such as autonomous car navigation systems, facial recognition, medical imaging, and satellite images analysis. Specifically, we focus on the enhancements in diagnostic accuracy, environmental monitoring, security, and safety that arose as a result of the adoption of artificial intelligence in these sectors through the use of case studies. Furthermore, we discuss the issues that are associated with artificial intelligence in image processing. These challenges include the necessity for explainable AI models, the requirement for computational resources, and the protection of data privacy. A number of potential solutions to these problems

关键词： Industries Image recognition Image analysis Transformers Satellite navigation systems Generative adversarial networks Satellite images Convolutional neural networks Security Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Blockchain Based Dead Reckoning navigation system for Fault detection and secure Communication over VANET

Blockchain Based Dead Reckoning navigation system for Fault ...

引用

New Frontiers in Communication, Automation, Management and Security (ICCAMS), International Conference on

作者： Haewon Byeon Ismail Keshta V. Mahalakshmi Mukesh Soni Ihtiram Raza Khan Ramya Maranan Department of Digital Anti-Aging Healthcare Inje University Gimhae Republic of Korea Computer Science and Information Systems Department College of Applied Sciences AlMaarefa University Riyadh Saudi Arabia Department of Computer Science College of Computer Science & Information Technology Jazan University Jazan Saudi Arabia Dr. D. Y. Patil Vidyapeeth Pune Dr. D. Y. Patil School of Science & Technology Tathawade Pune India Academician Jamia hamdard Delhi Department of Research and Innovation Saveetha School of Engineering SIMATS Chennai Tamil Nadu India

ISBN: (数字)9798350317060

ISBN: (纸本)9798350317077

This research paper presents a blockchain-based approach for fault detection and secure communication in vehicular ad hoc networks (VANETs). VANETs are an emerging technology that allows vehicles to communicate with each other and with the surrounding infrastructure to improve safety and efficiency on the roads. However, the decentralized and dynamic nature of VANETs makes them vulnerable to various types of attacks, including false data injection and communication interference. To address these challenges, the proposed approach utilizes blockchain technology to ensure the integrity and authenticity of data exchanged among vehicles and the infrastructure. The system also includes a fault detection mechanism that can detect and isolate faulty vehicles to prevent them from disrupting the communication network. However, VANETs are distinct from conventional mobile ad hoc networks due to the high mobility of vehicles, which creates dynamic network environments and frequent link interruptions that result in message loss. A hierarchical defect detection method based on dead reckoning is proposed to address these issues. The technique uses the dead reckoning model to predict the transmission time of pulse messages and builds a hierarchical detection architecture with Roadside Units (RSUs) functioning as static nodes. This architecture enhances the efficacy of VANET fault detection. The proposed method was validated by NS-2 simulations, demonstrating superior performance in terms of detection speed, accuracy, and detection burden compared to the baseline fault detection method.

关键词： Fault tolerance Dead reckoning Event detection Fault detection Fault tolerant systems Vehicular ad hoc networks Predictive models

来源：评论

学校读者我要写书评

暂无评论

One T Gate Makes Distribution Learning Hard

引用

Physical Review Letters 2023年第24期130卷 240602-240602页

作者： M. Hinsche M. Ioannou A. Nietner J. Haferkamp Y. Quek D. Hangleiter J.-P. Seifert J. Eisert R. Sweke Dahlem Center for Complex Quantum Systems Freie Universität Berlin 14195 Berlin Germany Joint Center for Quantum Information and Computer Science (QuICS) University of Maryland and NIST College Park Maryland 20742 USA Department of Electrical Engineering and Computer Science TU Berlin 10587 Berlin Germany Helmholtz-Zentrum Berlin für Materialien und Energie 14109 Berlin Germany Fraunhofer Heinrich Hertz Institute 10587 Berlin Germany

The task of learning a probability distribution from samples is ubiquitous across the natural sciences. The output distributions of local quantum circuits are of central importance in both quantum advantage proposals and a variety of quantum machine learning algorithms. In this work, we extensively characterize the learnability of output distributions of local quantum circuits. Firstly, we contrast learnability with simulatability by showing that Clifford circuit output distributions are efficiently learnable, while the injection of a single T gate renders the density modeling task hard for any depth d=nΩ(1). We further show that the task of generative modeling universal quantum circuits at any depth d=nΩ(1) is hard for any learning algorithm, classical or quantum, and that for statistical query algorithms, even depth d=ω[log(n)] Clifford circuits are hard to learn. Our results show that one cannot use the output distributions of local quantum circuits to provide a separation between the power of quantum and classical generative modeling algorithms, and therefore provide evidence against quantum advantages for practically relevant probabilistic modeling tasks.

关键词： Machine learning Quantum computation Quantum computing models Quantum gates

来源：评论

学校读者我要写书评

暂无评论

Edge AI-Based Dynamic Treatment Strategy Generation Model for Consumer Healthcare Technology

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Byeon, Haewon Alsaadi, Mahmood Quraishi, Aadam Shabaz, Mohammad Ahanger, Tariq Ahamed Keshta, Ismail Saidova, Feruza Soni, Mukesh Karumuri, Srinivasa Rao Inje University Department of AI and Software Gimhae50834 Korea Republic of Al-Maarif University College Department of computer science Al Anbar31001 Iraq Intervention Treatment Institute M.D. Research HoustonTX United States Model Institute of Engineering and Technology J and K Jammu India CoBA Prince Sattam Bin Abdulaziz University Department of Management Information Systems Saudi Arabia AlMaarefa University College of Applied Sciences Computer Science and Information Systems Department Riyadh Saudi Arabia Tashkent State University of Economics Department of Foreign languages Tashkent Uzbekistan Lovely Professional University Division of Research and Development Phagwara India VLSI-Microelectronics Lab Department of Electronics and Communication Engineering Andhra Pradesh Vaddeswaram Guntur522302 India

Edge AI-based reinforcement learning is less reliant on mathematical models and relies on experience to help with the design and optimization of Consumer Technology models, making it ideal for learning dynamic treatment techniques. However, the current research still has the following problems: 1. The optimality of the learned strategy is considered without taking risks into account, leading to strategies with certain risks. 2. The issue of distribution shift is ignored, resulting in learned strategies that are completely different from those of doctors. 3. The patient's historical observational data and treatments are ignored, making it difficult to accurately assess the patient's state, which in turn leads to the inability to learn the optimal strategy. Based on this, we propose the DOSAC-DTR dynamic treatment strategy model, which integrates Dead-ends and offline monitoring into the Actor-Critic framework. First, we consider the risk of treatment actions recommended by the learned strategy and incorporate the concept of Dead-ends into the Actor-Critic framework. Second, to mitigate the distribution shift problem, we integrate physician monitoring into the Actor-Critic framework. This approach achieves better performance, resulting in lower estimated mortality rates and higher Jaccard index scores. © 1975-2011 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Architecture of Data Anomaly Detection-Enhanced Decentralized Expert System for Early-Stage Alzheimer’s Disease Prediction

arXiv

引用

arXiv 2023年

作者： Behfar, Stefan Kambiz Behfar, Qumars Hosseinpour, Marzie Department of Information Systems Geneva School of Business Administration Switzerland Department of Computer Science and Technology University of Cambridge United Kingdom Department of Neurology Faculty of Medicine University Hospital Cologne University of Cologne Germany Institute of Business Informatics Faculty of Business Economics Hasselt University Belgium

Alzheimer’s Disease, a global health challenge, necessitates early and precise detection to enhance patient outcomes. Magnetic Resonance Imaging (MRI) offers significant diagnostic potential, but its effective analysis remains a formidable task. This study presents a groundbreaking decentralized expert system, which ingeniously merges blockchain technology with Artificial Intelligence (AI), integrating robust anomaly detection for patient-submitted data. Traditional diagnostic methodologies often result in delayed and imprecise predictions, particularly in the disease’s early stages. Centralized data repositories struggle to manage the immense volumes of MRI data, alongside persistent privacy concerns that impede collaborative efforts. Our innovative solution harnesses the power of decentralization to safeguard both data integrity and patient privacy, facilitated by blockchain technology. It not only emphasizes AI-driven MRI analysis but goes a step further by incorporating an architecure of a sophisticated data anomaly detection mechanisms. These mechanisms are designed to scrutinize patient-contributed data for various issues, including data quality problems and atypical findings within MRI images. Performing an exhaustive check of the correctness and quality of MRI images and biological information directly on-chain is not practical due to the computational complexity and cost constraints of blockchain platforms. Instead, such checks are typically performed off-chain, and the blockchain is used to record the results securely. This comprehensive approach empowers our decentralized app to provide more precise early-stage Alzheimer’s Disease prediction. Further, by merging the strengths of blockchain, AI, and anomaly detection, our aimed-system represents a pioneering step towards revolutionizing disease diagnostics. © 2023, CC BY.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Cloud-based Decentralized Smart Healthcare for Patient Monitoring on Deep Learning 2

Cloud-based Decentralized Smart Healthcare for Patient Monit...

引用

2nd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2023

作者： Arunachalam, Sripriya Shanthi, H.J. Sivagurunathan, G. Das, Shyamali Anand, D. Raj M, Thanga School of Computing Sciences Vels Institute of Science Technology & Advanced Studies - Vistas Computer Applications- Pg India Amet University Ecr Kanathur India St. Joseph's College of Engineering Omr Department of Electronics and Communication Engineering Chennai600119 India Cmr Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India Koneru Lakshmaiah Education Foundation Department of Cse AP Vaddeswaram India Persistent Systems Limited Pune India

ISBN: (纸本)9781665456302

Over the past few years, there has been a meteoric surge in the quantity of digital information available online for instantaneous sharing, persistent archiving, and inquiring. It has expanded the possibilities for using digital data that is both decentralised and ad hoc in order to make decisions quickly. At present, e-Healthcare is among the most sought-after sectors for EHR and telemedicine communication. Securing electronic health records (EHR) has become a topic of intense interest in recent years, with previous works employing a wide range of methods to better ensure the confidentiality and security of EHR at a reasonable price. There are a number of serious problems with the current research, including computational complexity, increased process time, information leakage, vulnerability to various assaults, scalability difficulty, etc. Clinical data analysis presents several difficulties, but disease prediction is one of the most significant ones. The suggested study aims to apply deep learning (DL) classification algorithms for disease prediction. A technique that utilises cloud computing, fog computing, and IoMT more recently has been presented for diagnosing illness. Fast DL classification analysis is performed in the fog layer. When compared to the alternative proposed model Bi-CNN, the healthcare model's efficiency in the Bi-LSTM simulation yields significantly better results: 97.31% of accuracy, 97.58% of recall, 96.90% of precision, 94.90% of F1-measure, 97.25% of specificity, and 94.80% of G-mean. © 2023 IEEE.

关键词： Fog computing

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：