检索结果-内蒙古大学图书馆

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： J. Alan Calderón Ch. E. Benjamín Barriga G. Julio C. Tafur Alan Ccarita John Lozano Rodrigo Urbizagástegui Applied Nanophysics Institute for Physics Technical University of Ilmenau Ilmenau Germany Engineering Department Mechatronics Engineering Master Program Pontificia Universidad Católica del Perú Perú Engineering Department Mechanical Engineering Master Program Pontificia Universidad Católica del Perú Perú Engineering Department Control Engineering and Automation Master Program Mechatronic Engineering Master Program Pontificia Universidad Católica del Perú Perú Northen (Artic) Federal University Named After MV Lomonosov Arkhangelsk Russian Federation Engineering Department Engineering Electronic Section Pontificia Universidad Católica del Perú Perú

ISBN: (纸本)9781665409858

An optimal waste collection is a very complicated task in different countries. However, this task is more intricate, when there is not an organized procedure between people, government and technology. In this research it was studied and proposed strategies, to optimize the waste collection by technical suggestions, that were based on mathematical analysis and new technologies applications of sensors based on nanostructures due to this kind of sensors have good performance to measure physical variables in not simple places and conditions, such as around waste. Hence the reason, this work is prepared to contribute in the development of sensors based on nanostructures according to detect the physical variables: temperature, humidity, infrared reflection, moreover carbon dioxide (CO2) and methane (CH4) gases, which help to monitor the consequences of a not correct waste *** dependence on central and local government rules of waste management, it could be possible to find solution about organized waste collection, in which every family and walkers in streets would have the task to select the organic and inorganic garbage before the government trucks take the contents of the garbage trash cans to the landfill garbage dumps. However, many times the trash cans are not taken on time by the government trucks and garbage from them are producing gases and decomposition that causes contamination that damages health. Therefore, in this work there are proposed designed intelligent sensors, which are fixed in the trash cans due to measure physical parameters to give alarm for administrators controllers of boxes and to enhance the garbage selections from homes and streets to the main garbage landfills of the city. In other side, there will not be right solution in the waste collection, no matter the high advantage technologies, while humans could not be sensitive under this problematic. There are cleaned areas in cities, as for example touristic places, nevertheless, there

关键词： Temperature sensors Temperature measurement Waste management Gases Temperature dependence Urban areas Nanostructures

来源：评论

学校读者我要写书评

暂无评论

Arbitrary extension of the antibubble lifetime

引用

Physical Review Fluids 2022年第6期7卷 L061601-L061601页

作者： W. Wang F. Lin X. Wei J. Zou S. Dorbolo Zhejiang University City College Department of Mechatronics Engineering Hangzhou 310015 China State Key Laboratory of Fluid Power and Mechatronic Systems Zhejiang University Hangzhou 310027 China Ningbo Research Institute Zhejiang University Ningbo 315048 China Zhejiang Normal University College of Engineering Jinhua 321004 China FNRS-CESAM-GRASP Physics Department B5 University of Liège B-4000 Liège Belgium

An antibubble is an uncommon fluid object with a unique structure: a liquid globule is wrapped by a thin air film, with the whole being immersed in a liquid bath. In short, the antibubble is the opposite of a soap bubble. The antibubble has been regarded as a promising candidate for various industrial applications since two components can be separated only by an air layer before mixing. However, the use of the antibubble is limited by the short lifetime (≈1 min) and the broad distribution of the lifetimes. We demonstrate a simple and efficient method to extend the lifetime of the antibubbles. The proposed system consists of a liquid surface covered by a layer of bubbles under which antibubbles are generated. The liquid is then vertically shaken. Above a given acceleration threshold that depends on the frequency, the lifetime of the antibubbles is significantly increased. Under vibrations, antibubbles were kept alive up to 13 h. As soon as the vibration is stopped, the antibubble collapses immediately. The antibubble popping can therefore be programmed. A model based on the dynamical air drainage in the air shell of the antibubble is proposed to account for these observations.

关键词： Drop & bubble phenomena Microfluidics Surface gravity waves Surface tension effects Thin fluid films

来源：评论

学校读者我要写书评

暂无评论

A Space Crawling Robotic Bio-Paw (Scrbp) Enabled by Triboelectric Sensors for Surface Identification

SSRN

引用

SSRN 2022年

作者： Hou, Xuyan Zhang, Li Gao, Guowei Liu, Yuhui Na, Zhonglai Xu, QingZhang Ding, Tianxiang Li, Long Chen, Tao Research Center of Aerospace Mechanism and Control School of Mechatronics Engineering Harbin Institute of Technology Harbin150080 China Department of MECHANICAL ENGINEERING FACULTY OF ENGINEERING Hong Kong Polytechnic University Hong Kong Shanghai Key Laboratory of Intelligent Manufacturing and Robotics School of Mechatronic Engineering and Automation Shanghai University Shanghai200444 China Jiangsu Provincial Key Laboratory of Advanced Robotics School of Mechanical and Electric Engineering Soochow University Suzhou215123 China

With the rapid development of space crawling robotics technology, tactile perception, a significant source for the robot to sense the external environment, has become the preferred solution to gather information in space. Sensors embedded in the robotic end-effector unit can collect and encode the large tactile data, allowing the robot to feel and perceive the real surroundings. Therefore, a space crawling robotic bio-paw (SCRBP) inspired by a cat paw, which performs as a compliant device and can flat the impulse force during the robot’s contact process to the target surface, is proposed in this paper. Meanwhile, a touch-sensing system embedded on SCRBP with self-powered sensors based on the triboelectric nanogenerator (TENG) technology is proposed which can provide the multi-dimensional sensation information in real time. By combining with machine learning (ML), the sensory system can be used for surface identification from the footfall process to the robot’s controller hub. In conclusion, SCRBP device proposed in this paper has obvious advantages in surface information acquisition, space adaptability, power consumption, cost, reliable signal and minimized data. Accordingly, SCRBP system shows fabulous potential in space robotics. © 2022, The Authors. All rights reserved.

关键词： End effectors

来源：评论

学校读者我要写书评

暂无评论

The Effect of Image Input Transformation from Inertial Measurement Unit Data on the Classification of Skateboarding Tricks 8th

The Effect of Image Input Transformation from Inertial Measu...

引用

8th International Conference on Robot Intelligence Technology and Applications, RiTA 2020

作者： Abdullah, Muhammad Amirul Ibrahim, Muhammad Ar Rahim Shapiee, Muhammad Nur Aiman Zakaria, Muhammad Aizzat Mohd Razman, Mohd Azraai Musa, Rabiu Muazu P. P. Abdul Majeed, Anwar Innovative Manufacturing Mechatronics and Sports Laboratory Faculty of Manufacturing and Mechatronic Engineering Technology Universiti Malaysia Pahang Pahang Malaysia Centre for Fundamental and Continuing Education Department of Credited Co-Curriculum Universiti Malaysia Terengganu Terengganu Malaysia Centre for Software Development and Integrated Computing Universiti Malaysia Pahang Gambang26000 Malaysia

ISBN: (纸本)9789811648021

This study aims to improve the classification of flat-ground tricks namely Ollie, Kickflip, Shove-it, Nollie and Frontside 180 through the identification of significant input image transformation on different transfer learning models. Six goofy skateboarders (23 years of age ± 5.0 years’ experience) executed five tricks for each type of trick repeatedly on a customized ORY skateboard (Inertial Measurement Unit (IMU) sensor fused) on a cemented ground. From the IMU data, six raw signals were extracted. The best input image transformation and transfer learning model were identified through two input image transformations synthesized, namely raw data (RAW) and Fast Fourier Transform (FFT), and six transfer learning models based on default arguments from the Keras library. The variation of the SVM models (via different hyperparameters) was evaluated both on input image transformation and on transfer learning model in classifying the skateboarding tricks. It was shown from the study that RAW input image on three transfer learning models (DenseNet121, InceptionResNetV2, and ResNet101) demonstrated the 100% accuracy on all train, train and validation dataset. It could be concluded that the proposed method is able to improve the classification of the skateboarding tricks well. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Classification Machine learning Skateboarding Support Vector Machine Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Developing a wearable MEMS-based wound monitoring system

引用

AIP Conference Proceedings 2023年第1期2581卷

作者： Doubt Simango Tawanda Mushiri Abid Yahya Ryan Bhebhura Department of Mechatronic Engineering School of Engineering Sciences & Technology Private Bag 7724 Off-Chirundu Road Chinhoyi Zimbabwe Department of Industrial and Mechatronics Engineering Faculty of Engineering & the Built Environment University of Zimbabwe Mt Pleasant 630 Churchill Avenue Harare Zimbabwe Botswana International University of Science & Technology Private Bag 16 Palapye Botswana Department of Mechatronic Engineering School of Engineering Sciences & Technology. Private Bag 7724 Off-Chirundu Road Chinhoyi Zimbabwe

Persistent injury research is still poorly understood. Continuous injuries do not follow the usual injury recovery cycle and remain at the flaming stage. Skin wounds and delayed wound healing are a concern in the general well-being domain. The cost of medical services is rising as a result of perplexing and slow methods. There is a growing demand for technology that can track the progress of healing and the physiological status of the skin in real-time for wounds that take a long time to heal. In this work, the researcher developed a system that uses biosensors to monitor wound healing by analyzing the wound's conditions and acting on the wound to promote healthy and rapid healing. This study will look at a variety of active and passive drug administration approaches in wound care. Micro-Electro-Mechanical Systems (MEMS) based technology has been used to continuously monitors wound parameters and assures safe healing. The study's goal is to create a system that examines the temperature, pH, pressure, and moisture levels of a wound. The conveyance stage's strategy and capacity to adjust drug dispersion are also taken into consideration. The framework will remotely deliver the signal to a cell phone. Analysts use the Global System for Mobile Communications (GSM) module to create innovative connections between the device and other fringe devices. MEMS devices have been most suited for accurately applying these drugs since the emergence of Hydrogels. The disposal of this gel necessitates a precise instrument, as this medicine is costly to get and must not be thrown away. MEMS system applications can be utilized to create more modern gadgets that can aid the medical sector of life, such as a blood pressure sensor used in hospitals to monitor blood pressure. Compared to present machinery that requires disinfection and recalibration, this technology hardware can be easily disposed of and replacement hardware may be swiftly created. The research article will assist in ident

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Classification of Skateboarding Tricks by Means of Support Vector Machine: An Evaluation of Significant Time-Domain Features 1

引用

11th Malaysian Technical Universities Conference on engineering and Technology, MUCET 2019

作者： Abdullah, Muhammad Amirul Ibrahim, Muhammad Ar Rahim Shapiee, Muhammad Nur Aiman Abdul Majeed, Anwar P. P. Mohd Razman, Mohd Azraai Musa, Rabiu Muazu Zakaria, Muhammad Aizzat Innovative Manufacturing Mechatronics and Sports Laboratory Faculty of Manufacturing and Mechatronic Engineering Technology Universiti Malaysia Pahang PekanPahang26600 Malaysia Department of Credited Co-Curriculum Centre for Fundamental and Continuing Education Universiti Malaysia Terengganu Kuala NerusTerengganu Malaysia

ISBN: (数字)9789811560255

ISBN: (纸本)9789811560248

This study aims to improve classification accuracy of different Support Vector Machine (SVM) models in classifying flat ground tricks namely Ollie, Kickflip, Shove-it, Nollie and Frontside 180 through the identification of significant time-domain features. An amateur skateboarder (23 years of age ±5.0 years’ experience) executed five tricks for each type of trick repeatedly on a customized ORY skateboard (IMU sensor fused) on a cemented ground. From the IMU data a total of 36 features were extracted through statistical measures. The significant features were identified through two feature selection methods, namely Pearson and Chi-Squared. The variation of the SVM models (kernel-based) was evaluated both on all features and selected features in classifying the skateboarding tricks. It was shown from the study that all classifiers improved significantly in terms of training accuracy, prediction speed, training time and test accuracy. The Cubic-based SVM and Quadratic-based SVM demonstrated a 100% accuracy on both the test and train dataset, however, the Cubic-based SVM model provided the fastest training time and prediction speed between the two models. It could be concluded that the proposed method is able to improve the classification of the skateboarding tricks well. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Brain tumor detection and classification based on machine learning systems

引用

AIP Conference Proceedings 2023年第1期2581卷

作者： Doubt Simango Tawanda Mushiri Abid Yahya Lazarus Nyanduwa Department of Mechatronic Engineering School of Engineering Sciences & Technology Private Bag 7724 Off-Chirundu Road Chinhoyi Zimbabwe Department of Industrial and Mechatronics Engineering Faculty of Engineering & the Built Environment University of Zimbabwe Mt Pleasant 630 Churchill Avenue Harare Zimbabwe Botswana International University of Science & Technology Private Bag 16 Palapye Botswana

As a growing country, Zimbabwe must adopt these technologies since they offer numerous benefits, including precision and accuracy. Because a significant volume of MRI data must be reviewed, this procedure takes long and is unsuitable for big data. Because automated solutions are more cost-effective, they are essential. Automated medical imaging has become a hot issue in a variety of medical diagnostic checking. Magnetic Resonance Imaging (MRI) tumor diagnosis that is automated is crucial because it provides information about abnormal tissues that are needed for treatment planning. Human inspection is the traditional approach for detecting defects in magnetic resonance brain imaging. This method is impractical when dealing with large amounts of data. As a result, radiologists are developing automated tumor detection technologies to save time. It is necessary to use MATLAB to train an artificial neural network to identify brain cancers. In addition, an algorithm that can distinguish and categorize tumors into carcinogenic and non-cancerous tumors must be developed. The complexity and variety of malignancies make MRI brain tumor diagnosis tough task. Machine learning approaches are utilized to detect malignancies in brain MRI in this study. In this research paper work, three stages are implemented in preprocessing on the brain. To extract texture features, the Gray Level Co-occurrence Matrix (GLCM) is used. They are then classified using a machine learning technique, indicating the feasibility of utilizing machine vision to discriminate between cancerous and non-cancerous brain tumors. As a result, an AI process is used to arrange them correctly, demonstrating the feasibility of using machine vision to distinguish between cancerous and non-malignant cerebrum growths. It has the potential to make patient management easier in the future. Computer vision is one of the most widely utilized technology technologies for skin cancer detection systems in most industrialized cou

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Classification of Skateboarding Tricks by Means of the Integration of Transfer Learning and Machine Learning Models 11th

The Classification of Skateboarding Tricks by Means of the I...

引用

11th Malaysian Technical Universities Conference on engineering and Technology, MUCET 2019

作者： Shapiee, Muhammad Nur Aiman Ibrahim, Muhammad Ar Rahim Razman, Mohd Azraai Mohd Abdullah, Muhammad Amirul Musa, Rabiu Muazu Abdul Majeed, Anwar P. P. Innovative Manufacturing Mechatronics and Sports Laboratory Faculty of Manufacturing and Mechatronic Engineering Technology Universiti Malaysia Pahang PekanPahang Darul Makmur26600 Malaysia Department of Credited Co-Curriculum Centre for Fundamental and Continuing Education Universiti Malaysia Terengganu Kuala TerengganuTerengganu Malaysia

ISBN: (纸本)9789811560248

Generally, the assessment of skateboarding tricks executions is completed abstractly dependent on the judges’ understanding and experience. Hence, an objective and means for assessing skateboarding tricks, especially in the big competition are important. This research aims at classifying skateboarding flat ground tricks, namely Ollie, Kickflip, Shove-it, Nollie Front Shove and Frontside 180 through camera vision and pre-trained convolution neural network for feature extraction coupled with a conventional machine learning model. An amateur skateboarder (23 years of age ± 5.0 years’ experience) executed five tricks for each type of trick repeatedly on a skateboard from a camera with a distance of 1.26 m. From the images captured, the features were engineered and extracted through Transfer Learning, particularly VGG-16 and then classified by means of Logistic Regression (LR) and k-Nearest Neighbour (k-NN) models. The observation from the preliminary investigation demonstrated that through the proposed methodology, the LR and k-NN models attained a classification accuracy of 99.1% and 97.7%, on the test dataset, respectively. It could be shown that the proposed strategy can classify the skateboard tricks well and would, in the long run, support the judges in providing an increasingly objective-based judgment. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

The Classification of Skateboarding Trick Manoeuvres: A Frequency-Domain Evaluation 1

引用

11th Malaysian Technical Universities Conference on engineering and Technology, MUCET 2019

作者： Ibrahim, Muhammad Ar Rahim Shapiee, Muhammad Nur Aiman Abdullah, Muhammad Amirul Razman, Mohd Azraai Mohd Musa, Rabiu Muazu Abdul Majeed, Anwar P. P. Innovative Manufacturing Mechatronics and Sports Laboratory Faculty of Manufacturing and Mechatronic Engineering Technology Universiti Malaysia Pahang PekanPahang Darul Makmur26600 Malaysia Department of Credited Co-Curriculum Centre for Fundamental and Continuing Education Universiti Malaysia Terengganu Kuala NerusTerengganu Malaysia

ISBN: (数字)9789811560255

ISBN: (纸本)9789811560248

The growing interest in skateboarding as a competitive sport requires new motion analysis approaches and innovative ways to portray athletes’ results as previous techniques in the identification of the tricks was often inadequate in providing accurate evaluation during competition. Therefore, there is a need to introduce an unprejudiced method of evaluation in skateboarding competitions. This paper presents the classification of five different skateboarding tricks (Ollie, Kickflip, Frontside 180, Pop Shove-it, and Nollie Frontside Shove-it) through the identification os significant frequency-domain signals collected via Inertial Measurement Unit (IMU) and the use of machine learning models. One male skateboarder (age: 23 years old) performed five different tricks repeatedly for several times. The time-domain data acquired from the IMU were converted to frequency-domain by employing Fast Fourier Transform (FFT) and a number of statistical features (mean, kurtosis, skewness, standard deviation, root mean square and peak-to-peak corresponding to x-y-z-axis of the IMU) were then extracted. Significant features were then identified from the Information Gain (IG) scoring. It was shown from the study that the Naïve Bayes (NB) classifier is able to acquire the highest classification accuracy of 100% on the test data compared to the other evaluated classifiers, namely Artificial Neural Network (ANN) and Support Vector Machine (SVM), by utilising the selected features, suggesting that the proposed methodology could provide an objective-based evaluation of the tricks. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Fast Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

An automated wound detection system

引用

AIP Conference Proceedings 2023年第1期2581卷

作者： Doubt Simango Tawanda Mushiri Abid Yahya Jacqueline Kiwa Department of Mechatronic Engineering School of Engineering Sciences & Technology Private Bag 7724 Off-Chirundu Road Chinhoyi Zimbabwe Department of Industrial and Mechatronics Engineering Faculty of Engineering & the Built Environment University of Zimbabwe Mt Pleasant 630 Churchill Avenue Harare Zimbabwe Botswana International University of Science & Technology Private Bag 16 Palapye Botswana Department of Information Systems Engineering School of Engineering Sciences & Technology Private Bag 7724 Off-Chirundu Road Chinhoyi Zimbabwe

A crucial measurement for the injury evaluation measure is assessing and following injury size. Great area and size assessments can help you choose the right treatment for you. Typically, laboratory wound healing plans include a series of photographs taken at regular intervals that show the wounded area and the healing interaction in a guinea pig, usually a mouse. These images are then examined in person to determine crucial measurements relevant to the research, such as wound size progression. Nonetheless, this task is time-consuming and exhausting; additionally, defining the injury edge can be abstract and move from one person to the next, even among experts. Furthermore, as our understanding of the recuperating interaction grows, we need to track these important factors effectively and precisely for high throughput (for instance, over the enormous scope and long haul tests). Following that, in this study, a calculation was created using Python in an OpenCV-based picture investigation pipeline using image processing techniques such as segmentation and classification, to allow non-uniform injury pictures and concentrating relevant data such as the area of premium, the injury only picture yields, and wound fringe size after some time measurements. To acquire acceptable results, camera positioning and distance from the wounds that need to be photographed are critical. In this case, ultrasonic sensors in the camera system are required to ensure that images are taken at a consistent distance. Because the injury space is properly created, appropriate recuperation procedures are addressed. Image processing using Python provided results in terms of area and estimated chemicals to deliver in the right amounts. In this way, wound healing can be tracked, and appropriate drug doses may be given based on the size of the wound. Furthermore, the wound healing trend can be easily assessed.

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：