检索结果-内蒙古大学图书馆

International Carpathian Control Conference (ICCC)

作者： Krzysztof Lalik Mateusz Kozek Faculty of Mechanical Engineering and Robotics AGH University of Science and Technology Krakow Poland

ISBN: (数字)9781728119519

ISBN: (纸本)9781728119526

Industry 4.0 which a characteristic feature is disappearance of the barrier between humans and machines, the use of cloud computing and the dissemination of so-called “Internet of Things” (IoT) enables global access to data and machines. An important pillar of Industry 4.0 is “machine intelligence”, which implies the autonomy of production processes, which can also include the organization of production and response to changes or prediction of the damages in demand for a product with specific parameters. This paper presents an intelligent diagnostic system, which is dedicated for implementation in Industry 4.0 ecosystem. The main feature of this solution is the Cloud communication enables Cloud computing of the predictive maintenance algorithms for the health monitoring of the construction under examination.

关键词： Resonant frequency Industries Synthetic aperture sonar Machine learning algorithms Production Cloud computing Pollution measurement

来源：评论

学校读者我要写书评

暂无评论

FireXnet: an explainable AI-based tailored deep learning model for wildfire detection on resource-constrained devices

引用

Fire Ecology 2023年第1期19卷 1-19页

作者： Ahmad, Khubab Khan, Muhammad Shahbaz Ahmed, Fawad Driss, Maha Boulila, Wadii Alazeb, Abdulwahab Alsulami, Mohammad Alshehri, Mohammed S. Ghadi, Yazeed Yasin Ahmad, Jawad Faculty of Engineering and Technology Multimedia University Melaka Malaysia School of Computing Engineering and the Built Environment Edinburgh Napier University Edinburgh UK Department of Cyber Security Pakistan Navy Engineering College NUST Karachi Pakistan Robotics and Internet of Things Laboratory Prince Sultan University Riyadh Saudi Arabia RIADI Laboratory National School of Computer Sciences University of Manouba Manouba Tunisia Department of Computer Science College of Computer Science and Information Systems Najran University Najran Saudi Arabia Department of Software Engineering Computer Science Al Ain University Abu Dhabi United Arab Emirates

Forests cover nearly one-third of the Earth’s land and are some of our most biodiverse ecosystems. Due to climate change, these essential habitats are endangered by increasing wildfires. Wildfires are not just a risk to the environment, but they also pose public health risks. Given these issues, there is an indispensable need for efficient and early detection methods. Conventional detection approaches fall short due to spatial limitations and manual feature engineering, which calls for the exploration and development of data-driven deep learning solutions. This paper, in this regard, proposes 'FireXnet', a tailored deep learning model designed for improved efficiency and accuracy in wildfire detection. FireXnet is tailored to have a lightweight architecture that exhibits high accuracy with significantly less training and testing time. It contains considerably reduced trainable and non-trainable parameters, which makes it suitable for resource-constrained devices. To make the FireXnet model visually explainable and trustable, a powerful explainable artificial intelligence (AI) tool, SHAP (SHapley Additive exPlanations) has been incorporated. It interprets FireXnet’s decisions by computing the contribution of each feature to the prediction. Furthermore, the performance of FireXnet is compared against five pre-trained models — VGG16, InceptionResNetV2, InceptionV3, DenseNet201, and MobileNetV2 — to benchmark its efficiency. For a fair comparison, transfer learning and fine-tuning have been applied to the aforementioned models to retrain the models on our dataset. The test accuracy of the proposed FireXnet model is 98.42%, which is greater than all other models used for comparison. Furthermore, results of reliability parameters confirm the model’s reliability, i.e., a confidence interval of [0.97, 1.00] validates the certainty of the proposed model’s estimates and a Cohen’s kappa coefficient of 0.98 proves that decisions of FireXnet are in considerable accordance with t

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning algorithm in image analysis with Augmented Reality headset for Industry 4.0 technology

Transfer Learning algorithm in image analysis with Augmented...

引用

Mechatronics Systems and Materials (MSM)

作者： Mateusz Kozek Faculty of Mechanical Engineering and Robotics AGH University of Science and Technology Krakow Poland

ISBN: (数字)9781728169569

ISBN: (纸本)9781728169576

Modern technology lines in Industry 4.0 standard use many complex smart systems to improve the speed of production. Manufacturing becomes more flexible and, on the other hand, more demanding for a process operator. This article presents mixed reality glasses that supports the work of the operator integrated via a cloud with a technology line. Transfer learning algorithm is shown in a set of artificial neural network algorithms belonging to the Deep Learning class to analyze the image from ML headset. This algorithm is designed to recognize the current occupation of the storage tray with direct transmission of information to the control and measurement system.

关键词： Robots Industries Training Augmented reality Headphones Neural networks

来源：评论

学校读者我要写书评

暂无评论

Comparative Numerical Analysis of a Piezoelectric Harvester Based on Non-auxetic and Auxetic Material

Comparative Numerical Analysis of a Piezoelectric Harvester ...

引用

International Carpathian Control Conference (ICCC)

作者： Dariusz Grzybek Wojciech Sikora Dariusz Kata Piotr Micek Faculty of Mechanical Engineering and Robotics AGH University of Science and Technology Cracow Poland

ISBN: (数字)9781728119519

ISBN: (纸本)9781728119526

This study presents a comparison of energy harvesting capability of cantilever beam harvester based on non-auxetic and auxetic material. The analysed harvester consisted of two layers: piezoelectric and carrying. Performed numerical calculations allowed to assess influence of an auxetic section in the carrying layer on stress distribution in the piezoelectric and amount of generated electric power. An analysis was conducted for two material variants of the carrying layer: steel and polymer. Presented results showed that energy harvesting efficiency can be increased by introducing auxetic region into the carrying layer of cantilever beam energy harvester.

关键词： Auxetic materials Strain Stress Structural beams Laser beams Geometry Steel

来源：评论

学校读者我要写书评

暂无评论

MEASUREMENTS OF ACOUSTIC RESPONSE OF CAR INTERIOR FOR STRUCTURAL EXCITATIONS

引用

Diagnostyka 2022年第4期23卷

作者： Paluch, Wojciech Klaczyński, Maciej BWI Poland Technologies sp. z o.o. ul. Kpt. Mieczyslawa Medweckiego 2 Balice32-083 Poland AGH University of Science and Technology Faculty of Mechanical Engineering and Robotics Department of Mechanics and Vibroacoustics Adama Mickiewicza 30 Kraków30-059 Poland

The transition from internal combustion to electric propulsion in cars presents component designers with new challenges in terms of noise reduction. Until now, components such as the suspension, its knocks were masked by the combustion engine or exhaust system. The absence of such significant sources, means that hitherto inaudible components are starting to become a nuisance. In order to reduce their noise, a number of optimisation solutions, both active and passive, are used. In order to do so, relevant measurements and data analysis must be carried out. This paper aims to present the acoustic characteristics of the interiors of two cars excited structurally in the vicinity of the front shock absorber mounting and by the operation of another component, the windscreen wipers on dry and wet windscreens. Measurements were made using 3D intensity probes based on acoustic particle velocity sensors. The results, in the form of both acoustic particle velocity and sound pressure characteristics and spectrograms, are presented comparatively for two types of car. © 2022 by the Authors.

关键词： Velocity control

来源：评论

学校读者我要写书评

暂无评论

Embodying pre-trained word embeddings through robot actions

arXiv

引用

arXiv 2021年

作者： Toyoda, Minori Suzuki, Kanata Mori, Hiroki Hayashi, Yoshihiko Ogata, Tetsuya Minori Toyoda is Faculty of Science and Engineering Waseda University Tokyo169-8555 Japan Kanata Suzuki is with Artificial Intelligence Laboratories Fujitsu Laboratories LTD. Kanagawa211-8588 Japan Faculty of Science and Engineering Waseda University Tokyo Japan Institute for AI and Robotics Future Robotics Organization Waseda University Tokyo169-8555 Japan Faculty of Science and Engineering Waseda University Tokyo Japan Faculty of Science and Engineering Waseda University National Institute of Advanced Industrial Science and Technology Tokyo100-8921 Japan

—We propose a promising neural network model with which to acquire a grounded representation of robot actions and the linguistic descriptions thereof. Properly responding to various linguistic expressions, including polysemous words, is an important ability for robots that interact with people via linguistic dialogue. Previous studies have shown that robots can use words that are not included in the action-description paired datasets by using pre-trained word embeddings. However, the word embeddings trained under the distributional hypothesis are not grounded, as they are derived purely from a text corpus. In this paper, we transform the pre-trained word embeddings to embodied ones by using the robot’s sensory-motor experiences. We extend a bidirectional translation model for actions and descriptions by incorporating non-linear layers that retrofit the word embeddings. By training the retrofit layer and the bidirectional translation model alternately, our proposed model is able to transform the pre-trained word embeddings to adapt to a paired action-description dataset. Our results demonstrate that the embeddings of synonyms form a semantic cluster by reflecting the experiences (actions and environments) of a robot. These embeddings allow the robot to properly generate actions from unseen words that are not paired with actions in a dataset. Copyright © 2021, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Solving the Time-Optimal Control Problem for Nonlinear Non-Autonomous Linearizable Systems

SSRN

引用

SSRN 2023年

作者： Sklyar, Katerina V. Ignatovich, Svetlana Yu. Sklyar, Grigory M. Department of Automatics and Robotics West Pomeranian University of Technology str. 26 Kwietnia 10 Szczecin71-126 Poland Department of Applied Mathematics V.N. Karazin Kharkiv National University Svobody sqr. 4 Kharkiv61022 Ukraine Faculty of Computer Science and Information Technology West Pomeranian University of Technology str. Zolnierska 49 Szczecin71-210 Poland Institute of Mathematics University of Szczecin Wielkopolska 15 Szczecin70-451 Poland

We present conditions under which the time-optimal control problem for a nonlinear non-autonomous linearizable system can be solved by the method of successive approximations, at each step of which a power Markov moment minproblem is solved. The proposed method can be efficiently implemented by use of symbolic and numerical calculations. © 2023, The Authors. All rights reserved.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Automated IR Image Segmentation for Identification of Overheated Idlers in Belt Conveyor Systems Based on Outlier-Detection Method

SSRN

引用

SSRN 2022年

作者： Barszcz, Tomasz Siami, Mohammad Wodecki, Jacek Zimroz, Radoslaw AMC Vibro Sp. z o.o. Pilotow 2e Kraków31-462 Poland Department of Robotics and Mechatronics AGH University of Science and Technology Al. Mickiewicza 30 Kraków30-059 Poland Faculty of Geoengineering Mining and Geology Wroclaw University of Science and Technology Na Grobli 15 Wroclaw50-421 Poland

Conveying systems play an essential role in the continuous horizontal transportation of raw materials in mining sites. Regular inspections of conveyor system structures and their components, especially idlers, are essential for proper maintenance. Traditional inspection methods are labor-intensive and hazardous. This paper proposes an automated method to determine overheated idlers. Input data is infrared (IR) and RGB videos of a conveyor system from a mobile robot. Such videos contain disturbances (e.g. sun reflections) which create difficulties to the segmentation of overheated idlers. The method is based on the outliers detection technique. Values of outliers in 8-bit grayscale histogram of extracted frames were considered as optimal threshold values. For the performance validation the shapes and locations of segmented hot spots were compared with RGB frames from the same scene. Furthermore, the segmentation results of four different global thresholding methods have been compared to the proposed method. © 2022, The Authors. All rights reserved.

关键词： Belt conveyors

来源：评论

学校读者我要写书评

暂无评论

Project of a 6 Degrees of Freedom Remotely Operated Vehicle propulsion system with azimuthal thrusters

Project of a 6 Degrees of Freedom Remotely Operated Vehicle ...

引用

OCEANS

作者： Tomasz Malachowski Filip Dudek Faculty of Mechanical Engineering and Robotics AGH University of Science and Technology Kraków Poland

ISBN: (数字)9781728154466

ISBN: (纸本)9781728184098

The control of underwater vehicles is a challenging task even in the era of highly efficient computing technology. Its difficulties consist of the properties of the underwater environment such as high nonlinearity, drag and disturbances and the expected vehicle performance, which should be able to fulfill its tasks precisely, safely and possibly quickly. Additionally, the miniaturization, availability and lowering costs of electronics created new possible applications for underwater vehicles. While in the case of a work-class Remotely Operated Vehicles (ROVs) the power efficiency and consumption is not the most significant aspect, it is very considerable in the case of smaller robots with limited power source. Nevertheless, the standard principles of actuating an ROV remained roughly unchanged over the years. Most units which are designed to move independently in all 6 Degrees of Freedom are equipped with a set of 8 thrusters which are fixed to the frame and provide no thrust vectoring, resulting in forces partially cancelling each other out. Due to the fact that the thrusters consume the majority of the energy supplied to the vehicle, this causes losses in efficiency. Widely used Open-loop control systems could also be an issue in which an experienced operator is needed in order to maneuver the vessel. The scope of this work is to propose and test an alternative solution with azimuthal thrusters, which could provide the same mobility in 6 DoF with reduced overall number of thrusters and thus improved power efficiency as well as better control based on closed-loop system with position feedback.

关键词： Attitude control Unmanned vehicles Resource management Task analysis Underwater vehicles Standards Robots

来源：评论

学校读者我要写书评

暂无评论

Acute Kidney Injury Detection using Real Human Urine NGAL Biomarker Sensor based on 3D Graphene

Acute Kidney Injury Detection using Real Human Urine NGAL Bi...

引用

Biomedical Engineering International Conference (BMEiCON)

作者： Netnapa Sittihakote Sirirat Anutrakulchai Adisorn Tuantranont Pobporn Danvirutai Chavis Srichan Department of Biomedical Engineering Faculty of Engineering Khon Kaen University Khon Kaen Thailand Department of Internal Medicine Faculty of Medicine Khon Kaen University Khon Kaen Thailand National Science and Technology Development Agency (NSTDA) Pathum Thani Thailand T Robotics Co. Ltd. Bang Kok Thailand Faculty of Engineering Khon Kaen University Khon Kaen Thailand

ISBN: (纸本)9781665489041

Acute kidney injury (AKI) is not a specified symptom in the early stages. Frequency of AKI occurrence is highly correlated to Chronic Kidney Disease (CKD). Therefore, development of non-invasive, ultra-sensitive, and highly accurate sensing platform is crucial for early AKI diagnosis. Serum creatinine (SCr) level usually takes 24-72 hours to response to the incident of AKI. Meanwhile, urine Neutrophil Gelatinase-Associated Lipocalin (NGAL) takes only 2 hours to response after the AKI occurrence. In this work, we investigated the use of microporous graphene and dipole-dipole enhancement between graphene/nickel layers to enhance electrode sensitivity for urine NGAL level determination. Selectivity was assured using enzymatic electrochemistry. Once NGAL level was measured, a doctor can diagnose AKI under additional information on patient’s conditions. The result is promising since the detection range was 0.110 to 93.9 ng/ml and the correlation coefficient is 0.8235. The detection covered AKI primary diagnostic cutoff level at 87 ng/ml in urine. The electrochemical immunosensor was able to determine NGAL in Urine with results compared to those provided by the standard ELISA method. This work is a part of development of handheld NGAL determination strip in human urine samples and prepared portable NGAL sensing devices. Despite our investigation’s limitation, the acquired data indicates that non-invasive acute kidney injury detection using actual human urine with graphene foam/nickel-based electrochemical sensor should be further explored as an auxiliary diagnostic tool for AKI.

关键词： Electrodes Electric potential Three-dimensional displays Sensitivity Graphene Biomedical measurement Chronic kidney disease

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：