检索结果-内蒙古大学图书馆

Emerging Research in Computational Science (ICERCS), International Conference on

作者： C. Madana Kumar Reddy Rakesh Chandrashekar K Nattar Kannan H Pal Thethi Srinivasarao Dharmireddi Ram Bajaj Department of Computer Applications Annamacharya Institute of Technology and Sciences Andhra Pradesh India Department of Mechanical Engineering New Horizon College of Engineering Bangalore Department of Artificial Intelligence and Machine Learning Saveetha Institute of Medical and Technical Sciences Chennai Lovely Professional University Phagwara India Department of Cybersecurity Louis Missouri USA Faculty of Basic and Applied Sciences RNB Global University Rajasthan India

Software Defined Network (SDN) has permitted revolutionary networking solutions by the separation of manage and statistics planes and the centralization of network administration. Nevertheless, SDN networks without robust get right of access to manage may be prone to protection breaches and unapproved gain admission to, consequently giving significant hazards. Rapid and accurate anomaly detection and access control are important in cloud-aspect collaborative networks, given to the fact permitted devices have the opportunity to turn malevolent. We suggest the exploitation of a modern cloud-primarily based collaboration network architecture that makes use of SDN and neural networks to solve these challenging circumstances. Attribute-Based Access management (ABAC) and smart contracts give accurate community device access management in our machine. In addition, we present a totally new approach for identifying anomalies in Cloud-Edge Collaborative (KPI) data with the assistance of the employment of an effective aggregate of GRU-GAN. This hybrid technique finds prevalent devices, enabling preemptive discount of dangers. This response moreover employs blockchain era to beautify protection. The decentralised and tamper-evident structure of blockchain promotes obtain right of entry to manage and ensures the integrity of community transactions. Experimental effects argue that our method discovers irregularities greater across datasets. Network integrity is secured by the implementation of popularity-based get right of access to rules, which minimise malicious tool assaults. This full strategy blends SDN, neural networks, and blockchain generation to defend cloud-location collaboration networks against unapproved get right of access to and criminal hobby. This specialised technique secures network assets and creates the basis for current day-day community infrastructures to be lasting and truthful.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Empirical Evaluation of Deep learning based Models for Time Series Datasets

引用

Procedia computer Science 2023年 230卷 864-873页

作者： Malav Champaneria Dhyani Panchal Jiten Bhalavat Hemant Yadav Dr. Nirav Bhatt Dr. Purvi Prajapati Dr. Nikita Bhatt Smt. K. D. Patel Department of Information Technology CSPIT Charotar University of Science and Technology Changa Gujarat India Dr. Nirav Bhatt Department of Artificial Intelligence and Machine Learning CSPIT Charotar University of Science and Technology Changa Gujarat India Dr. Nikita Bhatt U & P U. Patel Department of Computer Engineering CSPIT Charotar University of Science and Technology Changa Gujarat India

A deep learning-based method for predicting numerous time series is suggested in this study. For example, this paper contrasts the effectiveness of DeepAR, N- Beats, Transformer, Temporal Fusion Transformer, and other deep learning models. Our test findings demonstrate that deep learning models can anticipate with excellent accuracy across a variety of time series datasets. Moreover, our results indicate that the ideal input representation differs among datasets and that it plays a significant impact in predicting accuracy. Overall, our work gives practical advice for choosing the appropriate model and input representation, as well as insights into the use of deep learning models for predicting numerous time series.

关键词： Deep learning Temporal fusion transformer MTSA Time series forecasting deep neural network Deep AR Statistical model Auto ETS Transformer

来源：评论

学校读者我要写书评

暂无评论

IoT Security Based on machine learning

IoT Security Based on Machine Learning

引用

International Conference on Smart Technologies For Smart Nation (SmartTechCon)

作者： Rama Krishna Vanakamamidi L. Ramalingam N. Abirami S. Priyanka C. Sasi Kumar S. Murugan HCL Technology LTD Vijayawada Andhra Pradesh India Department of Artificial Intelligence and Machine Learning Chennai Institute of Technology (Autonomous) Chennai Tamil Nadu India Department of Information Technology R.M.D. Engineering College Chennai Tamil Nadu India Department of Computer Science and Engineering Muthayammal Engineering College (Autonomous) Namakkal Tamil Nadu India Department of Computer Science and Engineering Shree Sathyam College of Engineering and Technology Salem Tamil Nadu India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

The protection of user privacy and mitigation of threats like spoofing, DoS, jamming, and eavesdropping are essential for the Internets of Things (IoT) to fulfill its promise of bringing improved and intelligent services to users via the integration of diverse devices into networks. machine learning (ML) approaches, including supervised learning, unsupervised learning, and Reinforcement learning (RL), are explored as potential solutions for securing the IoT. This article focuses on the use of ML in IoT authentications, access controls, secured offloading, and malware detection strategies to safeguard sensitive information. The challenges of incorporating these ML-based security strategies into real-world IoT systems are also discussed. A complete analysis of the threats facing IoT networks is provided, as the methods already in use to protect against them and the need for securing such networks. Then, highlight the areas where these security solutions are lacking and might benefit from ML and DL methods. Finally, go through in-depth the current ML and DL methods for dealing with various IoT network security issues. Several potential research possibilities for IoT securities based on ML and DL are also discussed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-Time Health Data Analytics in IoT-Connected Wearable Devices

Real-Time Health Data Analytics in IoT-Connected Wearable De...

引用

Emerging Technology (INCET), International Conference for

作者： Jyostna Devi G S Venkatakiran V Nuthan Prasad Swathi Pai M KDV Prasad Sheetalrani Rukmaji Kawale Department of Electronics and Communication Engineering Sri Venkatesa Perumal College of Engineering (AUTONOMOUS) Andhra Pradesh India Department of Electronic and Communication MSRIT Bangalore Karnataka Dept. of Artificial Intelligence and Machine Learning NITTE (Deemed to be University) NMAM Institute of Technology Nitte Karnataka India Department of Research Symbiosis Institute of Business Management Hyderabad Symbiosis International (Deemed University) Pune India Department of Computer Science Karnataka State Akkamahadevi Women University Vijayapura Karnataka India

ISBN: (数字)9798350361155

ISBN: (纸本)9798350361162

This research paper focuses on the revolutionary effect of instant in-person health analytics by IoT -connected wearable medical devices on health results. By the exploration of currently available literature, technical systems and showing case studies, we provided strong evidence that real time monitoring improved patient outcome and made healthcare delivery better. The research unveils the remarkable sequestration of advancing wearable device technology that can capture and analyze essential health factors in the current state. Through our representation of the remote patient monitoring, chronic disease management, and fitness tracking trends, we show the effects of those advancements being clearly pronounced as early disease detection, personal interventions, and higher patient engagement. On the other hand we tackle the mentioned issues such as data privacy and security presenting new methods as possible options to minimize the dangers. Stakeholders in the healthcare and technology sector obtain useful information by analyzing the results of this study, as they can now explore the power of real-time health data analytics to completely change patient care and design upon healthcare delivery in the future.

关键词： Data analysis Accuracy Medical services Real-time systems User experience Stakeholders Security

来源：评论

学校读者我要写书评

暂无评论

UNDERSTANDING DOMAIN RANDOMIZATION for SIM-TO-REAL TRANSFER

arXiv

引用

arXiv 2021年

作者： Chen, Xiaoyu Hu, Jiachen Jin, Chi Li, Lihong Wang, Liwei Key Laboratory of Machine Perception MOE School of Artificial Intelligence Peking University China Department of Electrical and Computer Engineering Princeton University United States Amazon United States International Center for Machine Learning Research Peking University China

Reinforcement learning encounters many challenges when applied directly in the real world. Sim-to-real transfer is widely used to transfer the knowledge learned from simulation to the real world. Domain randomization-one of the most popular algorithms for sim-to-real transfer-has been demonstrated to be effective in various tasks in robotics and autonomous driving. Despite its empirical successes, theoretical understanding on why this simple algorithm works is limited. In this paper, we propose a theoretical framework for sim-to-real transfers, in which the simulator is modeled as a set of MDPs with tunable parameters (corresponding to unknown physical parameters such as friction). We provide sharp bounds on the sim-to-real gap-the difference between the value of policy returned by domain randomization and the value of an optimal policy for the real world. We prove that sim-to-real transfer can succeed under mild conditionswithout any real-world training samples. Our theory also highlights the importance of using memory (i.e., history-dependent policies) in domain randomization. Our proof is based on novel techniques that reduce the problem of bounding the sim-to-real gap to the problem of designing efficient learning algorithms for infinite-horizon MDPs, which we believe are of independent interest. Copyright © 2021, The Authors. All rights reserved.

关键词： Random processes

来源：评论

学校读者我要写书评

暂无评论

DGTD modeling of Mie scattering phenomenon of gold nano particles for biosensing applications

DGTD modeling of Mie scattering phenomenon of gold nano part...

引用

Clinical Biophotonics 2020

作者： Shree, Divya S. Malakareddy, Bharathi A. Uralakatte, Kavya P. Rajan, Bina Narayan, K. BMS Institute of Technology and Management Department of Computer Science and Engineering Department of Artificial Intelligence and Machine Learning Bangalore Karnataka India Sai Vidya Institute of Technology Department of Electronics and Communication Engineering Bangalore Karnataka India

ISBN: (纸本)9781510634961

Personal wearable medical devices and sensors have become more popular which results in better resources optimization and a better systematic monitoring or health condition. The ability to extract quantitative information in living cells without actual biopsy (disturbance in the structure of the cell) can be used to study and monitor morphological and physiological changes such as pre-cancerous or cancerous conditions. Basically, light scattered from a cell depends on the size of the cell, structure of the cell and the properties of the incident light. It is also termed as "optical biopsy". Such Mie scattering based Lab-on-a-Chip (LOC) sensor device if implemented can be used for early diagnosis of terminal diseases such as cancer. Gold nano particle acts as a sensor on this wearable device. Mie scattering based nonlinear optical phenomenon is used for cancer detection. This work involves modelling, simulation and analysis of a nano sensor using Discontinuous Gallerkin Time Domain method (DGTD). Light is used from arbitrary shaped objects at various incident angles. The Mie solution to Maxwell's equations describes the scattering of an electromagnetic plane wave by a homogeneous sphere. Mie scattering theory has been used to determine whether scattered light from tissue corresponds to healthy or cancerous cell nuclei using angle resolved low coherence interferometry. Gold nanoparticle has been used in biological applications and it is necessary to know the co-efficient of scattering and co-efficient of absorption. Mie scattering has no upper limits with respect to size of the particle. © 2020 SPIE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Recursive Feature Elimination based Multi-variate Naïve Bayes Classification for Product Recommendation

Recursive Feature Elimination based Multi-variate Naïve Bay...

引用

International Conference on Emerging Research in Electronics, computer Science and Technology (ICERECT)

作者： Parameshachari B. D S.G Gollagi Piyush Kumar Pareek Mohandas Karamthoti Electronics and Communications Engineering Nitte Meenakshi Institute of Technology Bengaluru India Computer Science & Engineering KLE College of Engineering and Technology Belagavi India Artificial Intelligence & Machine Learning Nitte Meenakshi Institute of Technology Bengaluru India Edu Infotech International Res Inc Atlanta Georgia State United States of America

Today's most important E-commerce apps are those that use the latest AI and machine learning technologies. Unlike humans, computers are unable to comprehend non-digital alternatives. Therefore, it is vital that consumers learn about things like food, clothing, and medicine. Human perceptions have certain limits, but expanding them is no easy feat. Because of the rapid development has quickly become a common way for people to make purchases and get content. Performing an efficient way to increase consumer happiness. Because of shifts in sequence length, textual order, and complex logic, imagining the true polarity of user evaluations remains a formidable challenge. It is recommended that SA work be broken down into four distinct phases: I data gathering (DC), (ii) pre-processing, (iii) features extraction (FE) or term weighting-(TW), (iv) feature-selection-(FS), and (v) polarity or sentiment classifications (SC). To begin, the data collection process begins with the Web Arguing Tool (WST) being used to scrape product reviews from E-commerce sites. The data acquired from the web scrape is then preprocessed. These cleaned data are further processed using Term Frequency-based inverse class frequency by passing them via TW and FS. The purpose of this study is to use two common Naive Bayes approaches—Classification—to determine if a review of a product is positive or negative. The optimal candidate feature subset is chosen by using a recursive feature elimination strategy on the data. The study also seeks to determine which of the two methods is more effective for the provided data. A ‘2’ yardstick dataset is used for comparing the proposed classifier to the current state of the art. Consequences show that, associated to state-of-the-art procedures, the suggested model provides the highest performance in SC

关键词： Support vector machines Measurement Deep learning TV Data collection Feature extraction Motion pictures

来源：评论

学校读者我要写书评

暂无评论

Society Security App

Society Security App

引用

Advances in Science and Technology (ICAST), International Conference on

作者： Reshma Kanse Harish Motekar Vinod Rathod Supriya Ajagekar Dhwaniket R. Kamble Trupti Patil Santosh Rathod Deparment of Artificial Intelligence and Machine Learning Bharati Vidyapeeth Deemed To Be University DET Navi Mumbai India Department of Computer Science and Engineering Bharati Vidyapeeth Deemed To Be University DET Navi Mumbai India Department of Computer Science and Business Systems Bharati Vidyapeeth Deemed To Be University DET Navi Mumbai India

ISBN: (纸本)9781665492645

In the housing society, daily life in urban areas has significant things to manage. Our daily necessities, such as water supply, electricity, security, and a variety of other things that are essential in residential life, fall under the purview of housing society management. In the majority of cases, society management practices a traditional method of correspondence. This absolutely has a few limitations and inconveniences. Everyday notices, month-to-month gatherings, comprehensive developments, various contacts for day-to-day needs, security alarms, high-priority communication, and numerous others may not be conveyed as expected in the ongoing situation, as the greater part of the things are getting dealt with physically. To overcome the issues caused by this time- consuming manual framework, an automated framework should be created to decrease human efforts. In most societies, work is done physically. Resident's contact information is noted on the papers. As all work is done on paper, it is undeniably challenging to oversee and monitor basically everything related to work expenses in society. This cooperative society management system will automate the entire daily life of the society. This system likewise keeps the contacts of specialized individuals or organizations that offer various types of assistance, like labour, housekeeping, pest control, equipment maintenance, and so on. There is no automated framework for all of the things that happen in society, so people can understand what's going on. This framework likewise raises invoices against all residents. This process for sustaining a society is designed to address the most widely recognized issues in societies. Utilizing this framework Advance installments or halfway instalments can be effortlessly noted and followed at any level. They require coordination among the society's management and the vendors, which offer some types of assistance, so the appropriate convenience can be given. In this maintenance bi

关键词： Urban areas Manuals Organizations Maintenance engineering Pest control Security Monitoring

来源：评论

学校读者我要写书评

暂无评论

Distilling the Unknown to Unveil Certainty

arXiv

引用

arXiv 2023年

作者： Zhao, Zhilin Cao, Longbing Zhang, Yixuan Lin, Kun-Yu Zheng, Wei-Shi The Data Science Lab School of Computing Macquarie University SydneyNSW2109 Australia The DataX Research Centre Macquarie University SydneyNSW2109 Australia The China-Austria Belt and Road Joint Laboratory on Artificial Intelligence and Advanced Manufacturing Hangzhou Dianzi University Zhejiang Hangzhou310005 China The School of Computer Science and Engineering Sun Yat-sen University Guangzhou510275 China The School of Computer Science and Engineering Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Sun Yat-sen University Guangzhou510275 China

Out-of-distribution (OOD) detection is essential in identifying test samples that deviate from the in-distribution (ID) data upon which a standard network is trained, ensuring network robustness and reliability. This paper introduces OOD knowledge distillation, a pioneering learning framework applicable whether or not training ID data is available, given a standard network. This framework harnesses unknown OOD-sensitive knowledge from the standard network to craft a certain binary classifier adept at distinguishing between ID and OOD samples. To accomplish this, we introduce Confidence Amendment (CA), an innovative methodology that transforms an OOD sample into an ID one while progressively amending prediction confidence derived from the standard network. This approach enables the simultaneous synthesis of both ID and OOD samples, each accompanied by an adjusted prediction confidence, thereby facilitating the training of a binary classifier sensitive to OOD. Theoretical analysis provides bounds on the generalization error of the binary classifier, demonstrating the pivotal role of confidence amendment in enhancing OOD sensitivity. Extensive experiments spanning various datasets and network architectures confirm the efficacy of the proposed method in detecting OOD samples. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

ASSISTIVE AI FOR AUGMENTING HUMAN DECISION-MAKING

arXiv

引用

arXiv 2024年

作者： Gyöngyössy, Natabara Máté Török, Bernát Farkas, Csilla Lucaj, Laura Menyhárd, Attila Menyhárd-Balázs, Krisztina Simonyi, András van der Smagt, Patrick Ződi, Zsolt Lőrincz, András Department of Artificial Intelligence ELTE Eötvös Loránd University Budapest Hungary Institute of the Information Society Ludovika University of Public Service Budapest Hungary Department of Computer Science and Engineering University of South Carolina ColumbiaSC United States Machine Learning Research Lab Volkswagen Group Munich Germany Department of Civil Law ELTE Eötvös Loránd University Budapest Hungary

Regulatory frameworks for the use of AI are emerging. However, they trail behind the fast-evolving malicious AI technologies that can quickly cause lasting societal damage. In response, we introduce a pioneering Assistive AI framework designed to enhance human decision-making capabilities. This framework aims to establish a trust network across various fields, especially within legal contexts, serving as a proactive complement to ongoing regulatory efforts. Central to our framework are the principles of privacy, accountability, and credibility. In our methodology, the foundation of reliability of information and information sources is built upon the ability to uphold accountability, enhance security, and protect privacy. This approach supports, filters, and potentially guides communication, thereby empowering individuals and communities to make well-informed decisions based on cutting-edge advancements in AI. Our framework uses the concept of Boards as proxies to collectively ensure that AI-assisted decisions are reliable, accountable, and in alignment with societal values and legal standards. Through a detailed exploration of our framework, including its main components, operations, and sample use cases, the paper shows how AI can assist in the complex process of decision-making while maintaining human oversight. The proposed framework not only extends regulatory landscapes but also highlights the synergy between AI technology and human judgement, underscoring the potential of AI to serve as a vital instrument in discerning reality from fiction and thus enhancing the decision-making process. Furthermore, we provide domain-specific use cases to highlight the applicability of our framework. © 2024, CC BY-SA.

关键词：

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：