检索结果-内蒙古大学图书馆

Iterative Feedback Tuning Algorithm for Tower Crane Systems

Procedia computer Science 2022年 199卷 157-165页

作者： Raul-Cristian Roman Radu-Emil Precup Elena-Lorena Hedrea Stefan Preitl Iuliu Alexandru Zamfirache Claudia-Adina Bojan-Dragos Emil M Petriu Politehnica University of Timişoara Dept. Automation and Applied Informatics Bd. V. Parvan 2 300223 Timişoara Romania University of Ottawa School of Electrical Engineering and Computer Science Ottawa Canada

This paper proposes validates an Iterative Feedback Tuning (IFT) algorithm, which is a classical and also popular data-driven algorithm, on tower crane systems. The IFT algorithm is applied to improve the performances of three proportional-integral (PI) controllers by solving an optimization problem. The IFT algorithm is validated using experiments to control the cart position, the arm angular position and the payload position. The experiments are conducted on a tower crane system in authors’ laboratory, and the experimental setup is laboratory equipment that has strong nonlinearities. Ten iterations are performed to highlight the control system performance using IFT controllers.

关键词： Iterative Feedback Tuning control algorithms tower crane systems

来源：评论

学校读者我要写书评

暂无评论

Enhance computing performance through deep learning and blockchain integration for public health problems 37

Enhance computing performance through deep learning and bloc...

引用

37th International Conference on Biomedical engineering, IBIOMED 2020

作者： Purnomo, Mauridhi H Fahruzi, Iman Anggraeni, Wiwik Dept of Electrical Engineering Dept of Computer Engineering Faculty of Intelligent Electrical and Informatics Technology Institut Teknologi Sepuluh Nopember Surabaya Indonesia Dept of Electrical Engineering Dept of Information Systems Faculty of Intelligent Electrical and Informatics Technology Institut Teknologi Sepuluh Nopember Surabaya Indonesia

ISBN: (纸本)9781728171562

Blockchain is one of the most phenomenal innovations and becomes an attraction to be widely implemented in public health. Blockchain manages and accesses various data sets distributed across all users. It requires tools that can solve this data processing problem. Deep learning can be used to analyses and process public data efficiently and rapidly. Blockchain and deep learning integration support efforts to address accuracy, latency, centralization, security, and privacy issues. This research proposes the concept and architecture of blockchain and deep learning integration for public health problems. Results show that deep learning is capable of classifying cases with more than 80% accuracy and dengue fever cases forecasting with average RMSE 10,39 © 2020 IEEE.

关键词： Public health

来源：评论

学校读者我要写书评

暂无评论

Photonic Neuromorphic Accelerator for Convolutional Neural Networks based on an Integrated Reconfigurable Mesh

arXiv

引用

arXiv 2024年

作者： Tsirigotis, Aris Sarantoglou, George Deligiannidis, Stavros Sánchez, Erica Gutierrez, Ana Bogris, Adonis Capmany, Jose Mesaritakis, Charis Dept. Information and Communication Systems Engineering University of the Aegean Palama 2 str Samos Karlovasi83200 Greece Dept. Informatics and Computer Engineering University of West Attica Ag. Spiridonos Egaleo12243 Greece iPronics Programmable Photonics Valencia Spain Photonics Research Labs Universitat Politècnica de València Camino de Vera Valencia46022 Spain

In this work, we present and experimentally validate a passive photonic-integrated neuromorphic accelerator that uses a hardware-friendly optical spectrum slicing technique through a reconfigurable silicon photonic mesh. The proposed scheme acts as an analogue convolutional engine, enabling information preprocessing in the optical domain, dimensionality reduction and extraction of spatio-temporal features. Numerical results demonstrate that utilizing only 7 passive photonic nodes, critical modules of a digital convolutional neural network can be replaced. As a result, a 98.6% accuracy on the MNIST dataset was achieved, with a power consumption reduction of at least 26% compared to digital CNNs. Experimental results confirm these findings, achieving 97.7% accuracy with only 3 passive nodes. Copyright © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Study on Text Feature Selection Using Ant Colony and Grey Wolf Optimization

A Study on Text Feature Selection Using Ant Colony and Grey ...

引用

International Conference on informatics and Computing (ICIC)

作者： Joan Angelina Widians Retantyo Wardoyo Sri Hartati Doctoral Program dept. of Computer Science and Electronics Universitas Gadjah Mada Dept. of Informatics Faculty of Engineering Universitas Mulawarman Samarinda Indonesia Dept. of Computer Science and Electronics Faculty of Mathematics and Natural Sciences Universitas Gadjah Mada Yogyakarta Indonesia

ISBN: (纸本)9798350345728

Text classification (TC) is widely used for organizing digital documents. The issues in TC are numerous characteristics and high-element dimensions. Many pattern classification issues require feature selection (FS), which is pertinent. FS removes unneeded and redundant data from the dataset. The Ant Colony Optimization (ACO) and Grey Wolf Optimizer (GWO) for FS are the main topics of our thorough assessment of the literature on the Swarm Intelligence (SI) algorithm. Furthermore, it illustrates how the hybrid SI technique is used in FS across various sectors. The hybrid SI technique uses applicable data from various FS methods to find feature subsets with smaller sizes and better classification performance than those found by regular FS algorithms.

关键词： Ant colony optimization Text categorization Pattern classification Filtering algorithms Feature extraction Classification algorithms Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Success stories from consumer technology-helping and saving lives

Success stories from consumer technology-helping and saving ...

引用

2021 Zooming Innovation in Consumer Technologies Conference, ZINC 2021

作者： Tonacci, Alessandro Billeci, Lucia Kakarountas, Athanasios Gamboa, Patricia Rogado, Jesus Lozano Institute of Clinical Physiology Pisa Italy University of Thessaly Dept. of Computer Science and Biomedical Informatics Lamia Greece Plux Wireless Biosignals S.A. Lisbon Portugal University of Extremadura Dept. of Electric Electronic and Automatic Engineering Badajoz Spain

ISBN: (纸本)9781665404174

Consumer technology (CT) has a broad amount of fields of application, among which one of the most important ones is represented by healthcare and well-being. Thanks to the quick technological development of ICT, CT have become widespread throughout the citizenship, allowing one to easily self-monitor his/her physiological parameters, checking for eventually dangerous values that could require the assistance from a medical doctor or caregiver. This panel session aims at presenting some CT solutions supporting healthcare during the life cycle of an individual, from early days until later life, providing hints about some of the possible conditions representing the major threats to healthy life throughout the years. © 2021 IEEE.

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

Mental Health Professionals' Insights on Digital Health Solutions for Anxiety in the UAE

Mental Health Professionals' Insights on Digital Health Solu...

引用

IEEE International Requirements engineering Conference Workshops (REW)

作者： Mariam Al Meqbaali Sofia Ouhbi Reem K Jan Leena Amiri Fadwa Al Mugaddam Mohamed Adel Serhani Nazar Zaki Dept. Computer Science & Software Engineering CIT UAEU Al Ain UAE Dept. Information Technology Uppsala University Uppsala Sweden Mohammed Bin Rashid University of Medicine and Health Sciences Dubai UAE Dept. Psychiatry and Behavioral Science CMHS UAEU Al Ain UAE College of Computing and Informatics University of Sharjah Sharjah UAE

ISBN: (数字)9798350395518

ISBN: (纸本)9798350395525

In recent years, anxiety disorders have become more prevalent worldwide, leading to an increased demand for mental healthcare services. Barriers such as stigma and cost, limit access to these services, prompting the exploration of alternative solutions. Digital technology shows significant promise in improving access to mental healthcare services. This study aims to explore the preferences, and concerns of Mental Health Professionals (MHPs) regarding digital health solutions for self-management of anxiety disorders in the UAE via an online survey. Participation was voluntary and anonymous, with 18 MHPs taking part. The survey included 12 questions covering demographics and key design elements. Most respondents displayed positive attitudes toward integrating digital anxiety solutions in the UAE, providing feedback and highlighting considerations. 61% endorsed the use of digital technology in anxiety disorder treatment, while 94% favored mindfulness exercises for anxiety management. 72% expressed interest in utilizing technology for therapy. Notable concerns raised included privacy and dependency. Guided by MHPs insights, we propose a conceptual framework for the design of digital anxiety solutions in the UAE. This framework prioritizes cultural appropriateness and language accessibility, offering solutions in Arabic and English. It encompasses diverse features, including a blended approach, treatment approaches, and relaxation techniques, to address anxiety disorders and ensures user safety through risk assessment and management. This framework can assist developers of digital anxiety solutions by highlighting the features and elements that MHPs deem most important.

关键词： Surveys Privacy Anxiety disorders Medical treatment Mental health Safety Electronic healthcare

来源：评论

学校读者我要写书评

暂无评论

Implementation and Application of an Intelligibility Protocol for Interaction with an LLM

arXiv

引用

arXiv 2024年

作者： Srinivasan, Ashwin Bania, Karan Shreyas, V. Mestha, Harshvardhan Liu, Sidong Dept. of Computer Science & Information Systems BITS Pilani Goa Campus Goa India APPCAIR BITS Pilani Goa India Dept. of Chemistry BITS Pilani Goa Campus Goa India Dept. of Electrical and Electronics Engineering BITS Pilani Goa Campus Goa India Centre for Health Informatics Macquarie University Sydney Australia

Our interest is in constructing interactive systems involving a human-expert interacting with a machine learning engine on data analysis tasks. This is of relevance when addressing complex problems arising in areas of science, the environment, medicine and so on, which are not immediately amenable to the usual methods of statistical or mathematical modelling. In such situations, it is possible that harnessing human expertise and creativity to modern machine-learning capabilities of identifying patterns by constructing new internal representations of the data may provide some insight to possible solutions. In this paper, we examine the implementation of an abstract protocol developed for interaction between agents, each capable of constructing predictions and explanations. The PXP protocol, described in [12] is motivated by the notion of "two-way intelligibility" and is specified using a pair of communicating finite-state machines. While the formalisation allows the authors to prove several properties about the protocol, no implementation was presented. Here, we address this shortcoming for the case in which one of the agents acts as a "generator" using a large language model (LLM) and the other is an agent that acts as a "tester" using either a human-expert, or a proxy for a human-expert (for example, a database compiled using human-expertise). We believe these use-cases will be a widely applicable form of interaction for problems of the kind mentioned above. We present an algorithmic description of general-purpose implementation, and conduct preliminary experiments on its use in two different areas (radiology and drug-discovery). The experimental results provide early evidence in support of the protocol’s capability of capturing one- and two-way intelligibility in human-LLM in the manner proposed in [12]. © 2024, CC BY.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Wideband Aperture-Coupled Array Design for Automotive Radar Applications

Wideband Aperture-Coupled Array Design for Automotive Radar ...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Lazaros Alexios Iliadis Achilles D. Boursianis Panagiotis Sarigiannidis Zaharias D. Zaharis Sotirios P. Sotiroudis Maria S. Papadopoulou Christos G. Christodoulou Sotirios K. Goudos ELEDIA@AUTH School of Physics Aristotle University of Thessaloniki Thessaloniki Greece Department of Informatics and Telecommunications Engineering University of Western Macedonia Kozani Greece Department of Electrical and Computer Engineering Aristotle University of Thessaloniki Thessaloniki Greece Dept. of Information and Electronic Eng. International Hellenic University Sindos Greece Department of Engineering and Computing The University of New Mexico USA Department of Electronics and Communication Engineering Bharath University Chennai Tamilnadu India

Advanced driver assistance systems (ADAS) technology has been developed to improve driver safety and is a major part of today's autonomous vehicle functionalities. Automotive radars operate as core sensors in modern ADAS systems since they can detect the speed and range of objects near the vehicle. This work uses a recent variant of the Runge-Kutta algorithm, namely RUN, to design an aperture-coupled antenna array for automotive radars. The proposed array consists of five U-shaped patch elements and achieves low return loss, high gain, and high efficiency at 77 GHz - 81 GHz.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Load Balancing Algorithm for 5G Vehicular Cloud Computing Systems 24

A Load Balancing Algorithm for 5G Vehicular Cloud Computing ...

引用

24th Pan-Hellenic Conference on informatics, PCI 2020

作者： Zoumi, Eirini Skondras, Emmanouil Veliu, David Michalas, Angelos Vergados, Dimitrios D. Dept. of Informatics University of Piraeus Piraeus Greece Dept. of Electrical and Computer Engineering University of Western Macedonia Kozani Greece

ISBN: (纸本)9781450388979

5G Vehicular Cloud Computing (5G-VCC) infrastructures are evolving rapidly. In a 5G-VCC system, Cloud resources should be efficiently distributed to provide satisfactory Quality of Service (QoS) for modern services with increased requirements. Furthermore, the workload should be fairly distributed to the available Virtual Machines (VMs). This paper proposes an algorithm for performing load balancing in Cloud infrastructures that exist in 5G-VCC systems. The algorithm is called Modified Ant Colony Optimization (MACO), as its functionality is influenced by the natural behaviour of ants. Specifically, the MACO algorithm assigns a pheromone (weight) value to each VM. Subsequently, for each service request the VM with the highest pheromone is selected in a way similar to the one that ants apply to select optimal routes. The selection of each VM results in the decrement its pheromone value, considering the workload of the assigned service. Evaluation results show that the proposed algorithm outperforms existing load balancing algorithms in terms of the processing time required for serving the user requests. © 2020 ACM.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Heart Failure: Machine Learning Prediction Within a 5-Year Framework

Heart Failure: Machine Learning Prediction Within a 5-Year F...

引用

IEEE Symposium on Bioinformatics and Bioengineering (BIBE)

作者： Konstantina-Helen Tsarapatsani Vasilios D. Tsakanikas Antonis Sakellarios Hans J. Trampisch Efterpi Karapintzou Henrik Rudolf George K. Matsopoulos Dimitrios I. Fotiadis Biomedical Research Institute Foundation for Research and Technology-Hellas Ioannina Greece Department of Medical Informatics Biometry and Epidemiology Ruhr University Bochum Bochum Germany Dept. of Materials Science and Engineering Unit of Medical Technology and Intelligent Information Systems University of Ioannina Greece Institute for Biostatistics and Informatics in Medicine and Ageing Research University Medical Center Rostock Germany School of Electrical and Computer Engineering National Technical University of Athens Athens Greeece Dept. of Materials Science and Engineering Unit of Medical Technology and Intelligent Information Systems University of Ioannina and Biomedical Research Institute-FORTH Ioannina Greece

ISBN: (数字)9798331518622

ISBN: (纸本)9798331518639

Heart failure (HF) is a complex syndrome that is affected by many factors and causes. It is crucial to early recognize the disease subtypes and the unidentified clinical pathways that give rise to it. Machine learning (ML) is the tool that assist to deal with these challenges and improve the prediction of HF. In this work, the HF risk prediction was implemented by employed ML classifiers, such as Random Forest (RF), Extreme Grading Boosting (XGBoost) and Light Gradient-Boosting Machine (LGBM). We utilized the data from the German epidemiological trial on ankle brachial index - getABI cohort, which includes 6,454 patients. The performance of classifiers was estimated by Accuracy (ACC), Sensitivity, Specificity and the area under the receiver operating characteristic curve (AUC) in mean values for each ML classifier. The results were also interpreted using the Explainable artificial intelligence (XAI) approach, the Shapley Additive exPlanations (SHAP) values. Our work reveals that LGBM classifier predict the HF risk within 5 years follow-up in general population with 68 % accuracy. Moreover, the N-terminal pro-B-type natriuretic peptide (NT-proBNP) was identified as the most important feature for HF risk prediction.

关键词： Accuracy Sensitivity Explainable AI Biological system modeling Peptides Receivers Predictive models Indexes Cardiovascular diseases Random forests

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：