检索结果-内蒙古大学图书馆

Automation and Computation (AUTOCOM), International Conference on

作者： Pavan Chaudhary Amritpal Sidhu Chinmayee Nayak Sidhant Das Kantharaj I K K.Naresh Kumar Thapa Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India Centre for Artificial Intelligence and Machine Learning Siksha ‘O’ Anusandhan (Deemed to be University) Bhubaneswar Odisha India Chitkara Centre for Research and Development Chitkara University Baddi Himachal Pradesh India School of Engineering and Technology Mechaical Engineering JAIN (Deemed to be University) Bangalore Karnataka Department of Electrical and Electronics Engineering Sathyabama Institute of Science and Technology Chennai Tamil Nadu India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

Ultra-Wideband Technology has garnered a reputation as an enabler of advancing industrial automation and robotics applications. UWB sensors emit short pulses of electromagnetic radiation to measure and can deliver highly accurate and real-time data over long distances. Compared to other sensing technologies, UWB sensors have a remarkably broad frequency spectrum and provide high data rates at low power. There are several advantages of UWB sensors implemented in industrial automation and robotics. These are done in a lab with some reference; you can take the data offline. UWB sensors can complement and be used in integration with other technologies, such as lidar or vision systems, to achieve higher performance results for a complete perception of the environment. This allows better and more efficient decision-making for autonomous systems. UWB sensors deliver highly accurate and repeatable measurements for robotic movement monitoring and control. They are also used for asset monitoring and inventory control, which finally help logistics & SCM. UWB sensors also improve workplace safety by warning about potential collisions or other hazardous conditions.

关键词： Automation Accuracy Service robots Production Robot sensing systems Sensors Safety Collision avoidance Monitoring Ultra wideband technology

来源：评论

学校读者我要写书评

暂无评论

Network Virtualization Empowered Metaverse: A Hierarchical Matching Approach

TechRxiv

引用

TechRxiv 2023年

作者： Khan, Latif U. Guizani, Mohsen Yaqoob, Ibrar Al-Fuqaha, Ala Erbad, Aiman Han, Zhu The Department of Machine Learning Mohamed Bin Zayed University of Artificial Intelligence United Arab Emirates The AICF Institute Charles Sturt University BathurstNSW2795 Australia The Hamad Bin Khalifa University Qatar The Electrical and Computer Engineering Department University of Houston HoustonTX77004 United States The Computer Science Department University of Houston HoustonTX77004 United States

Metaverse has generated significant interest for enabling wireless systems due to its self-sustainability and proactive analytic capabilities. It enables the deployment of meta spaces featuring avatars and digital twins for various real-world applications. However, it has become challenging to efficiently deploy meta spaces on edge/cloud environments while managing communication and computing resources effectively. In this paper, we propose a novel network virtualization framework within a shared system to make the deployment of meta spaces for various metaverse applications cost-efficient. The framework abstracts, isolates, and facilitates the sharing of wireless and computing resources, thereby enhancing flexibility and efficiency for metaverse-driven applications. It involves three key players: network operators (selling resources), metaverse operators (managing transactions), and end-users (purchasing resources). An optimization problem is formulated to optimize the wireless resource allocation, computing resource allocation, association of end-devices with meta spaces deployed at the network operators’ base stations, communication resource cost, and computing resource cost. We address the formulated NP-Hard mixed integer non-linear programming (MINLP) problem using decomposition, convex optimization, and hierarchical matching. Numerical results confirm the validity of the proposed approach. © 2023, CC BY.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Development of a machine learning Model for pulmonary carcinoma Prediction using computer Tomography (CT) Images

Development of a Machine Learning Model for pulmonary carcin...

引用

International Conference on Image Information Processing

作者： Jampani Chandra Sekhar Priyanshu Singh T. Rajesh Kumar G. Mahendran Katta Subba Rao Ramya Maranan Department of Computer Science and Engineering NRI Institute of Technology Guntur Andhra Pradesh India Department of Computer Science and Engineering R.V. College of Engineering Bengaluru Karnataka India Department of Artificial Intelligence and Machine Learning Sri Krishna College of Technology Coimbatore Tamil Nadu India Department of Mechanical Engineering R.M.K Engineering College Kavaraipettai Chennai Tamil Nadu India Department of Computer Science and Engineering B V Raju Institute of Technology Narsapur Medak (District) Telangana India Department of Research and Innovation Saveetha School of Engineering SIMATS Chennai Tamil Nadu India

ISBN: (数字)9798350371406

ISBN: (纸本)9798350371413

In this study, computer tomography (CT) scans are used to build a machine learning model for predicting lung cancer. A dataset of 10,000 CT scan images from 900 patients was used to train a group of machine learning algorithms. The objective is to identify the most reliable algorithm for lung cancer detection. The algorithms CNN, CNN with gradient descent, VGG-19, and VGG-16 have all been used in real-world applications. Each algorithm is trained using the dataset to create a prediction model. Performance metrics including accuracy, precision, specificity, sensitivity, and F-Score are taken into account when assessing how effective the algorithms are. The results demonstrate that the CNN model outperforms the competition with a 97% accuracy rate. The superior accuracy, specificity, sensitivity, and F-Score of the CNN model enable accurate lung cancer detection in CT scan images. The outcomes demonstrate that, utilising the well-established machine learning paradigm, the CNN algorithm, in particular, has substantial potential for early lung cancer diagnosis and prediction. Correctly identifying lung cancer from CT scan images allows for the implementation of focused treatment programmes and prompt interventions, ultimately leading to better patient outcomes. The study emphasises the requirement for applying machine learning methods to identify relevant characteristics and patterns in CT scan images. machine learning models can now be used in clinical settings to support the precise detection and treatment of lung cancer. The use of powerful algorithms and extensive datasets allowed for this accomplishment. In order to validate and enhance the models that have been developed, more study is needed in this field. The models will therefore be more useful and suitable for use in actual clinical settings. Utilising larger datasets, deep learning architectures, and other possible machine learning advancements can significantly increase the precision and generalizability of

关键词： machine learning algorithms Sensitivity Computed tomography Computational modeling Lung cancer machine learning Predictive models

来源：评论

学校读者我要写书评

暂无评论

Spectral, Probabilistic, and Deep Metric learning: Tutorial and Survey

arXiv

引用

arXiv 2022年

作者： Ghojogh, Benyamin Ghodsi, Ali Karray, Fakhri Crowley, Mark Department of Electrical and Computer Engineering Machine Learning Laboratory University of Waterloo WaterlooON Canada Department of Statistics and Actuarial Science David R. Cheriton School of Computer Science Data Analytics Laboratory University of Waterloo WaterlooON Canada Department of Electrical and Computer Engineering Centre for Pattern Analysis and Machine Intelligence University of Waterloo WaterlooON Canada

This is a tutorial and survey paper on metric learning. Algorithms are divided into spectral, probabilistic, and deep metric learning. We first start with the definition of distance metric, Mahalanobis distance, and generalized Mahalanobis distance. In spectral methods, we start with methods using scatters of data, including the first spectral metric learning, relevant methods to Fisher discriminant analysis, Relevant Component Analysis (RCA), Discriminant Component Analysis (DCA), and the Fisher-HSIC method. Then, large-margin metric learning, imbalanced metric learning, locally linear metric adaptation, and adversarial metric learning are covered. We also explain several kernel spectral methods for metric learning in the feature space. We also introduce geometric metric learning methods on the Riemannian manifolds. In probabilistic methods, we start with collapsing classes in both input and feature spaces and then explain the neighborhood component analysis methods, Bayesian metric learning, information theoretic methods, and empirical risk minimization in metric learning. In deep learning methods, we first introduce reconstruction autoencoders and supervised loss functions for metric learning. Then, Siamese networks and its various loss functions, triplet mining, and triplet sampling are explained. Deep discriminant analysis methods, based on Fisher discriminant analysis, are also reviewed. Finally, we introduce multi-modal deep metric learning, geometric metric learning by neural networks, and few-shot metric learning. Copyright © 2022, The Authors. All rights reserved.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Cloud-Based Smart Sensing System for Real-Time Health Management of Dementia Patients

Cloud-Based Smart Sensing System for Real-Time Health Manage...

引用

International Conference on Smart Technologies For Smart Nation (SmartTechCon)

作者： R. Latha R. Ramya U. Arul Nilamadhab Mishra S. Dhanalakshmi Professor Department of Computer Science and Engineering K. Ramakrishnan College of Engineering Trichy Tamil Nadu India Department of Mathematics S.A Engineering College Chennai Tamil Nadu India Professor Department of Artificial Intelligence and Machine Learning Saveetha School of Engineering Saveetha Institute of Medical And Technical Sciences Chennai Tamil Nadu School of Computing Science and Engineering VIT Bhopal University Madhya Pradesh India Assistant Professor Department of Electronics and Communication Engineering Sri Muthukumaran Institute of Technology Chennai Tamil Nadu India

The paper describes an innovative technique of monitoring updates on the health of people with dementia by integrating smart sensing technologies with a cloud-based platform. Because dementia is a degenerative neuropsychiatric disease that develops with time, constant patient monitoring is essential for ensuring the health and safety of those living with the condition. The proposed system uses smart sensing devices, including wearable and ambient sensors, to monitor dementia patients' health in real-time. Data like heart rates, movements used, and ambient conditions are collected and sent to a server in the cloud for analysis. The camera can monitor and analyze visual data, capture crucial information, and help evaluate the patient's well-being. Multiple patients can be monitored effectively in real time because of the cloud-based system's scalability, accessibility, and storage capacities. For healthcare providers to recognize irregular movements, identify possible risks to health, and implement preventative measures, doctors utilize the moment data analytics devices to gather valuable insights from the acquired data. In addition, the cloud-based solution improves collaborative care and enhances patient support by allowing for continuous communication and information sent among caregivers, doctors, nurses, and family members. Predefined thresholds or anomalous occurrences may trigger alerts and messages, allowing for quick action in reaction to emergencies. Modern technology and data analytics increase the health and happiness of people with dementia.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automated Digitally Modulated Signal Recognition and Classification using machine learning with Multimodal Information

Automated Digitally Modulated Signal Recognition and Classif...

引用

Augmented intelligence and Sustainable Systems (ICAISS), International Conference on

作者： Kalaiarasi N Md. Abul Ala Walid Shyamali Das Nanmaran R Srimathi S Beschi I S Department of ECE RMK College of Engineering And Technology Department of Computer Science and Engineering Khulna University of Engineering & Technology (KUET) Department of Artificial Intelligence and Machine Learning CMR Institute of Technology Bengaluru Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamilnadu India Department of Bio Technology Saveetha School of Engineering SIMATS Chennai Tamilnadu India Department of Computer Applications St. Joseph's College (Arts & Science) Chennai

Recently, the pattern detection of communication modulation signals takes obtained important attention in many application regions like civilian field, military, and so on. It develops vital to proposal a safe and robust feature extraction (FE) system to effectively detect the many signal modulation varieties in a difficult platform. Many works have developed novel approaches for extracting the feature parameters like instant features, fractal features, etc. Besides, machine learning (ML) algorithms are generally utilized for modulation signal classification. This study develops an Automated Digitally Modulated Signal Recognition and Classification using machine learning (ADMSR-ML) technique. The aim of the ADMSR-ML approach lies in the proficient recognition and categorization of various kinds of digitally modulated signals. At the initial stage, Sevcik Fractal Dimension (SFD) model is employed to produce a set of feature vectors. For modulation detection and classification, deep extreme learning machine (DELM) model is applied. Eventually, artificial Bee Colony (ABC) optimization algorithm was used for the optimal parameter selection of the DELM model. To examine the classification results of the ADMSR-ML approach, series of experiment are made. The extensive outcomes indicate the superior performance of the ADMSR-ML technique over other models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Maximizing Cloud Security: Empirical Evaluation of an Efficient Identity oriented Signature Verification Scheme for Wireless Networks

Maximizing Cloud Security: Empirical Evaluation of an Effici...

引用

Communication & Computing (WCONF), World Conference on

作者： C. Anitha V Praveena. V Samuthira Pandi Srivardhan Kumar B. Shiva A. Muniyappan Department of CSE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India Department of Artificial Intelligence and Machine Learning S.A. Engineering College Chennai Tamil Nadu India Centre for Advanaced Wireless Integrated Technology Chennai Institute of Technology Chennai Tamil Nadu India Department of Electrical and Electronics Engineering MLR Institute of Technology Hyderabad India Department of Computer Science and Engineering CMR College of Engineering and Technology Medchal Hyderabad India Centre for Computational Modeling Chennai Institute of Technology Chennai Tamil Nadu India

ISBN: (数字)9798350395327

ISBN: (纸本)9798350395334

A reliable and effective way to aggregate large amounts of data is very desirable in the area of wireless networks that are helped by cloud computing. Target tracking and environmental management are only two examples of the many real-world uses of wireless sensor networks. The cloud does, however, make data vulnerable to a variety of threats, including data eavesdropping and data contamination. Elevated Identity based Signature Verification (EISV) is an identity-based aggregate signature verification scheme that is cross-validated with the conventional Attribute based Encryption (ABE) security scheme to evaluate the efficiency of the proposed scheme for data integrity security in wireless sensor networks. This technique will reduce storage and bandwidth costs in wireless sensor networks while keeping data private, according to the benefits of aggregate signatures. With online signature methods, the signer can generate an electronic signature using a pre-calculated digital signature when a document is submitted. Applications involving wireless sensor networks with limited resources benefit greatly from such approaches. Our suggested technique, Elevated Identity based Signature Verification, has been implemented, and the results show that it is practical and feasible to utilize in a cloud based wireless sensor network configuration.

关键词： Cloud computing Wireless sensor networks Handwriting recognition Target tracking Wireless networks Aggregates Data integrity Computational modeling Secure storage Testing

来源：评论

学校读者我要写书评

暂无评论

Rethinking Wireless Communication Security in Semantic Internet of Things

arXiv

引用

arXiv 2022年

作者： Du, Hongyang Wang, Jiacheng Niyato, Dusit Kang, Jiawen Xiong, Zehui Guizani, Mohsen Kim, Dong In The School of Computer Science and Engineering Nanyang Technological University Singapore The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore Machine Learning Department Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates The Department of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of

Semantic communication is an important participant in the next generation of wireless communications. Enabled by this novel paradigm, the conventional Internet-of-Things (IoT) is evolving toward the semantic IoT (SIoT) to achieve significant system performance improvements. However, traditional wireless communication security techniques for bit transmission cannot be applied directly to the SIoT that focuses on semantic information transmission. One key reason is the lack of new security performance indicators. Thus, we have to rethink the wireless communication security in the SIoT. As such, in the paper, we analyze and compare classical security techniques, i.e., physical layer security, covert communications, and encryption, from the perspective of semantic information security. We highlight the differences among these security techniques when applied to the SIoT. Novel performance indicators such as semantic secrecy outage probability (for physical layer security techniques) and detection error expectation (for covert communication techniques) are proposed. Considering that semantic communications can raise new security issues, we then review attack and defense methods at the semantic level. Finally, we present several promising directions for future secure SIoT research. © 2022, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Feature Subset Selection for Big Data Via Parallel Chaotic Binary Differential Evolution Island Model Under Apache Spark

SSRN

引用

SSRN 2022年

作者： Yelleti, Vivek Vadlamani, Ravi Radha Krishna, P. Analytics Lab Centre for Artificial Intelligence Machine Learning Institute for Development and Research in Banking Technology Castle Hills Road #1 Masab Tank Hyderabad500076 India Department of Computer Science and Engineering National Institute of Technology Warangal506004 India

Feature subset selection (FSS) using a wrapper approach is essentially a combinatorial optimization problem having two objective functions viz., (i) the cardinality of the selected feature subset, and (ii) the area under the ROC curve (AUC) of a classifier built on this subset. They should be minimized and maximized respectively. In this paper, we propose a novel multiplicative single objective function involving cardinality and AUC for FSS in high-dimensional and large-scale datasets. Since the randomness involved in the Binary Differential Evolution (BDE) may yield less diverse solutions and get the algorithm entrapped in local minima, we embed Logistic and Tent Chaotic maps into the BDE, called Chaotic Binary Differential Evolution (CBDE). We (i) develop an adaptive version of CBDE based on SHADE (called CSHADE) and (ii) propose a scalable island (IS) based parallelization approach, where the data is divided into multiple partitions/islands thereby enabling the solutions evolve individually and get combined eventually in a migration strategy/policy. The results empirically show that the proposed parallel Chaotic BDE (P-CBDE-IS) and its corresponding adaptive version can find better quality feature subsets than the Parallel BDE (P-BDE-IS). Overall, P-CBDE-IS performed best in most of the cases. Logistic Regression (LR) is used as a classifier owing to its simplicity and power. The speedup attained by the proposed parallel approach signifies its importance. © 2022, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Policy Representation via Diffusion Probability Model for Reinforcement learning

arXiv

引用

arXiv 2023年

作者： Yang, Long Huang, Zhixiong Lei, Fenghao Zhong, Yucun Yang, Yiming Fang, Cong Wen, Shiting Zhou, Binbin Lin, Zhouchen School of Artificial Intelligence Peking University Beijing China College of Computer Science and Technology Zhejiang University China MOE Frontiers Science Center for Brain and Brain-Machine Integration College of Computer Science Zhejiang University China Institute of Automation Chinese Academy of Sciences Beijing China School of Computer and Data Engineering NingboTech University China College of Computer Science and Technology Hangzhou City University China

Popular reinforcement learning (RL) algorithms tend to produce a unimodal policy distribution, which weakens the expressiveness of complicated policy and decays the ability of exploration. The diffusion probability model is powerful to learn complicated multimodal distributions, which has shown promising and potential applications to RL. In this paper, we formally build a theoretical foundation of policy representation via the diffusion probability model and provide practical implementations of diffusion policy for online model-free RL. Concretely, we character diffusion policy as a stochastic process induced by stochastic differential equations, which is a new approach to representing a policy. Then we present a convergence guarantee for diffusion policy, which provides a theory to understand the multimodality of diffusion policy. Furthermore, we propose the DIPO, which implements model-free online RL with DIffusion POlicy. To the best of our knowledge, DIPO is the first algorithm to solve model-free online RL problems with the diffusion model. Finally, extensive empirical results show the effectiveness and superiority of DIPO on the standard continuous control Mujoco benchmark. © 2023, CC BY.

关键词： Reinforcement 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：