检索结果-内蒙古大学图书馆

IEEE Conference on Decision and Control

作者： Ahmed Ali Chiara Gabellieri Antonio Franchi Robotics and Mechatronics Department Electrical Engineering Mathematics and Computer Science (EEMCS) Faculty University of Twente Enschede Netherlands Department of Computer Control and Management Engineering Sapienza University of Rome Rome Italy

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

We propose a new multirotor aerial vehicle class of designs composed of a multi-body structure in which a main body is connected by passive joints to links equipped with propellers. We have investigated some instances of such class, some of which are shown to achieve omnidirectionality while having a minimum number of inputs equal to the main body Degrees of Freedom DoF’s, only uni-directional positive thrust propellers, and no internal forces generated at steady state. After dynamics are derived following the Euler-Lagrange approach, an I/O dynamic feedback linearization strategy is then used to show the controllability of any desired pose with stable zero dynamics. We finally verify the developed controller with closed-loop simulations.

关键词： Three-dimensional displays Propellers Dynamics Controllability Regulation Steady-state Feedback linearization Control theory Closed loop systems Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Preoperative imaging in primary hyperparathyroidism patients using 4DCT subtraction maps, a report of three cases

引用

Radiology Case Reports 2023年第8期18卷 2814-2822页

作者： Krol, Jorian P. Veerbeek, Tessa Deden, Laura N. Joosten, Frank B.M. Slump, Cornelis H. Oyen, Wim J.G. Department of Radiology & Nuclear Medicine Rijnstate Hospital Arnhem Netherlands Department of Robotics and Mechatronics Faculty of Electrical Engineering Mathematics and Computer Sciences University of Twente Enschede Netherlands Department of Biomedical Sciences and Humanitas Clinical and Research Centre Department of Nuclear Medicine Humanitas University Milan Italy Department of Radiology & Nuclear Medicine Radboud University Medical Centre Nijmegen Netherlands

Four-dimensional computed tomography (4DCT) is one of the preoperative imaging modalities that can be used to localize a parathyroid adenoma in primary hyperparathyroidism patients however, sensitivity differs in literature and could be improved especially for multiglandular hyperplasia or double adenomas. The most robust feature on the 4DCT for the differentiation between parathyroid adenoma and thyroid gland tissue is arterial enhancement. To make this better visible, we have developed a subtraction map that shows arterial enhancement as a color scale to increase sensitivity for 4DCT. In this report of 3 cases, we present the usefulness of this subtraction map in a 54-year-old male, a 57-year-old female and a 51-year-old male. Subtraction maps may increase sensitivity for 4DCT, especially for multiglandular hyperplasia or double adenomas. © 2023

关键词： Four dimensional computed tomography Parathyroid adenoma Parathyroid hyperplasia Primary hyperparathyroidism Subtraction map

来源：评论

学校读者我要写书评

暂无评论

A Study of Cantaloupe Fruit Classification Using Deep Learning Algorithms

A Study of Cantaloupe Fruit Classification Using Deep Learni...

引用

2024 International Conference on Control, robotics and Informatics, ICCRI 2024

作者： Tran, Huy Q. Le, Quoc Ngoc Ha, Cheolkeun Van Nguyen, Tan Tan, Quoc Phan Nguyen Tat Thanh University Robotics and Mechatronics Research Group Faculty of Engineering and Technology Viet Nam Faculty of Information and Technology SaigonTech Ho Chi Minh City Viet Nam University of Ulsan Department of Aerospace Engineering Ulsan Korea Republic of Thu Dau Mot University Faculty of Engineering and Technology Viet Nam Saigon University Faculty of Information Technology Viet Nam

ISBN: (纸本)9798350380309

This study focuses on identifying cantaloupes using deep learning algorithms. Subsequently, the cantaloupes are categorized into two groups (green and yellow) based on their distinct shape and color characteristics. We also recognized the unripe cantaloupe using several recent deep-learning algorithms. Experimental results from the dataset collected in Tay Ninh province, Vietnam, demonstrated classification accuracies of Yolov8, SSD Mobilenet V2, and Faster - RCNN are impressive, especially the Yolov8 model, which achieved an average accuracy of nearly 97%. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Active Capsule System for Multiple Therapeutic Patch Delivery: Preclinical Evaluation

Active Capsule System for Multiple Therapeutic Patch Deliver...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Jihun Lee Hoang Manh Cuong Jayoung Kim Eunho Choi Hyeonwoo Kee Seungun Yang Jong-Oh Park Sukho Park Department of Robotics and Mechatronics Engineering Daegu Gyeongbuk Institute of Science and Technology (DGIST) Republic of Korea Korea Institute of Medical Microrobotics (KIMIRo) Gwangju Republic of Korea

Recently, active research has been conducted on the therapeutic functions of capsule endoscopes. Here, we propose an active capsule system that captures images of the interior of the gastrointestinal tract (GI) and actively delivers therapeutic patches. The active capsule system mainly comprises therapeutic patches, an active capsule equipped with a camera, and a robot-assisted magnetic actuator. The active capsule moves inside the GI tract via a magnetic actuator using a robot, captures pictures of the GI tract in actual time, and performs hemostatic treatment by delivering therapeutic patches to the target lesions. First, the fundamental performance of the active capsule system was verified via a hemostatic performance test of the therapeutic patch, patch contamination prevention test of the active capsule, and basic actuation test of the capsule. Second, multiple therapeutic patches were delivered to the gastric surface in an ex vivo test using an active capsule system. Finally, as a preclinical test, it was confirmed that the GI tract examination and the therapeutic patches delivery were possible using the active capsule system through an animal test using a porcine. Consequently, the proposed active capsule system represents a new paradigm for capsule endoscopy with multiple therapeutic patch delivery capabilities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of Knee Joint for Transfemoral Amputees

Design and Analysis of Knee Joint for Transfemoral Amputees

引用

2021 International Conference on Artificial Intelligence and mechatronics Systems, AIMS 2021

作者： Qadir, Muhammad Usman Khan, Muhammad Awais Hussain, Muzammal Ul Haq, Izhar Akhtar, Nizar Shah, Kmaran Advanced Robotics Automation Lab University of Engineering Technology Dept. of Mechatronics Engineering Peshawar Pakistan University of Engineering Technology Dept. of Mechatronics Engineering Peshawar Pakistan International Committee of Red Cross Sanaa Yemen

ISBN: (纸本)9781665424820

Lower limb amputation not only reduces mobility but also results in significant impairment in quality of life. Microprocessor based transfemoral knee joints have gained significant importance in the last decade to not only restore cosmetics but also provide functionality comparable to real limb. One of the key issues in such devices is selection of the suitable material for manufacturing of knee joint to minimize chances of failure under various loading conditions, while at the same time ensuring the weight of the knee is within acceptable limits. The purpose of this research is to design a microprocessor-based knee joint and perform various static structural analysis for different materials to optimize strength to weight ratio of the proposed design. Initially, a model for the proposed microprocessor-based knee was developed in SolidWorks followed by displacement study and computation of von-mises stresses in Ansys Workbench. Different materials used in the analysis include Plain Carbon Steel, Stainless Steel 304, Aluminum 6061. Based on the results Aluminum 6061 was identified as a suitable material for manufacturing knee joint as it not only reduces weight of the knee joint but also the deformation and stress values are within acceptable limits. The minimum and maximum Von Mises stress of Aluminum 6061 was 559.9 Pa and 71.37 MPa respectively with tensile strength of 313 MPa. © 2021 IEEE.

关键词： Manufacture

来源：评论

学校读者我要写书评

暂无评论

Explainable Deep Learning for Brain-Computer Interfaces through Layerwise Relevance Propagation

Explainable Deep Learning for Brain-Computer Interfaces thro...

引用

International Winter Workshop on Brain-Computer Interface (BCI)

作者： Vladislav Mun Berdakh Abibullaev Computer Science Department School of Engineering and Digital Sciences Nazarbayev University Kazakhstan Robotics and Mechatronics Department School of Engineering and Digital Sciences Nazarbayev University Kazakhstan

With an ever-growing demand for BCI-based systems, numerous algorithms and machine learning systems have been proposed over the past few decades. Although state-of-theart approaches have reached practically appropriate levels of accuracy, most are often regarded as black-box models, which need more explainability. However, for cases where a Neural Network is used as the base for a classifier, a Layerwise Relevance Propagation (LRP) approach can be utilized to analyze the decision boundaries considered by the network. By calculating the importance of the neuron in each layer, the LRP can also be used as an effective model complexity reduction technique through the inactivation (pruning) of the neural pathways. The following work investigates the usability of the LRP framework in the field of BCI. This study provides an example of the practical application of the LRP with respect to the EEG (ERP) dataset, along with visual heatmap and scalp map examples of the LRP. Furthermore, the work analyzes the impact of network pruning on heatmap visualization and the model’s accuracy while also practically determining the maximum cutoff range for pruning BCI models.

关键词： Heating systems Deep learning Analytical models Visualization Brain modeling Transformers Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Towards the Optimal Design and Control of Solar-biomass Heating Networks for Greenhouse Applications: Methodology and Preliminary Results

Towards the Optimal Design and Control of Solar-biomass Heat...

引用

ISES Solar World Congress 2021

作者： Gil, Juan D. Ramos-Teodoro, J. Martínez, M. Sánchez-Molina, J.A. Pérez, M. CIESOL Research Center on Solar Energy Joint Center UAL-CIEMAT Spain Automatic Control Robotics and Mechatronics Group University of Almería Spain

ISBN: (纸本)9783982040875

Greenhouses are productive facilities very suitable for the consideration of distributed schemes for their energy management, including solar radiation as one of their main primary sources. This paper focuses on the optimal sizing and control of solar-biomass heating networks to be used in greenhouse environments. The methodology employed is a bi-level optimization strategy in which the lower layer, which is based on the energy hubs concept, is responsible for the optimal dispatch of the heating network, trying to reduce the operating costs while meeting demand. The upper layer includes a surrogate optimization algorithm in charge of performing the optimal sizing of the heating network to minimize the investment and long-term operating costs. Besides, this optimization problem includes some constraints such as the minimum desired solar fraction. A case study based on real facilities located in Almería (Southeast of Spain) is employed as an application example in order to show the promising outcomes achieved with the proposed methodology. The preliminary results are analyzed, regarding the economic viability, by means of the discount payback time and Levelized cost of energy. © 2021. The Authors. Published by International Solar Energy Society Selection and/or peer review under responsibility of Scientific Committee.

关键词： Operating costs

来源：评论

学校读者我要写书评

暂无评论

Design of an Iot-Enabled Scalable Closed Hydroponics System with Intelligent Parameter Control and Persistent Sensing Error Resilience

SSRN

引用

SSRN 2024年

作者： Chowdhury, M.D. Sameer Iqbal Ronoue, Mikdam-Al-Maad Asaduzzaman, Md. Jamal, Lafifa Department of Robotics and Mechatronics Engineering University of Dhaka Dhaka1000 Bangladesh Department of Agriculture and Food Technology Faculty of Bioenvironmental Sciences Kyoto University of Advanced Science Kyoto621-8555 Japan

The growing threat of climate change and global warming highlights the need for Controlled Climate Agriculture (CCA). Extreme weather patterns endanger the global food supply, making hydroponics an emerging alternative to traditional farming. Automated hydroponics systems with Internet of Things (IoT) capabilities have been implemented worldwide, demonstrating their potential for small and large-scale operations. Our proposed system builds on previous automated hydroponics work, monitoring and controlling key physical parameters for optimal plant growth, with the novel addition of CO2 gas supplementation and regulation for such systems. Two experimental iterations tested the system's efficacy under different weather conditions. Using data from the first experiment, we trained and tested multiple machine-learning models to create an intelligent control action classifier. The XGBoostClassifier performed best, achieving 0.98 accuracy, with 0.97 recall, 0.96 precision, and 0.96 F1-score. We also proposed and implemented a persistent error resilience algorithm developed as a constrained optimization problem. This involved a cost function and an adaptive multi-parameter λ-weighted minimization approach with update policies. Two experiments growing green leaf lettuce compared our system against soil-based and manual Deep Water Culture (DWC) methods. Results showed significantly higher fresh mass yield in our system. Our proposed system (P1) outperformed both soil-based (P2) and manual Deep Water Culture (DWC) methods (P3), with P1 producing 78.1% higher fresh mass yield than P2 and 168.8% higher than P3 in the first experiment. In the second experiment, P1's superiority was even more pronounced, with 288.1% higher yield than P2 and 141.9% higher than P3. Optimized on the first experiment data and implemented in the second, the error resilience algorithm reduced erroneous sensor data instances by approximately four times compared to conventional threshold and bandpass filte

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Rapidly developable low cost and power-efficient portable turbine-based emergency ventilator 8

Rapidly developable low cost and power-efficient portable tu...

引用

8th International Conference on Biomedical and Bioinformatics Engineering, ICBBE 2021

作者： Razwanul Haque, Syed Maruf Hossain, A K M Sudan Saha, Shovon Rahman Sohag, Md Hasanur Rabbi Shafi, Fozle Ranjan Sarkar, Satya CRUX Technologies Bangladesh Bioforge Health Systems Limited Bangladesh and Department of Robotics and Mechatronics University of Dhaka Bangladesh Oishi Electronics Sylhet Bangladesh

ISBN: (纸本)9781450385077

The use of ventilators has always been common in medical scenarios but very expensive to procure or develop. One of the main reasons for these is the components that are being used are expensive and require precise instrumentation, research and development. This paper attempts to mitigate that problem by proposing a novel way to rapidly develop a portable ventilator that uses common 3D printing technology and off-the-shelf components. This turbine and valve-based ventilator feature most of the modes that are commonly used by healthcare professionals. A unique servo-based pressure release mechanism has been designed that makes the system around 36 times more efficient than solenoid-based systems. Reliability and efficiency have been increased further through the use of a novel positive end-expiratory pressure (PEEP) valve that does not contain any electromechanical component. Effective algorithms such as feed-forward and proportional-integral-derivative (PID) controllers were used alongside the unique ĝ€Sensor data filtration methodology'. The system also provides an interactive graphical user interface (GUI) via an android application that can be installed on any readily found tabs while the firmware manages the breathing detection algorithm using a flow meter. This modular and portable ventilator also features a swappable battery and holds the ability to run on solar power. This energy-efficient and low noise system can run for 5 to 6 hours at a stretch without needing to be connected with the main's supply. This ventilator's design and development files have been certified by open-source hardware association (OSHWA): https://***/*** © 2021 ACM.

关键词： 3D printers

来源：评论

学校读者我要写书评

暂无评论

Intention-Conditioned Long-Term Human Egocentric Action Forecasting

arXiv

引用

arXiv 2022年

作者： Mascaró, Esteve Valls Ahn, Hyemin Lee, Dongheui Vienna Austria Ulsan Korea Republic of The Institute of Robotics and Mechatronics German Aerospace Center Wessling Germany

To anticipate how a person would act in the future, it is essential to understand the human intention since it guides the subject towards a certain action. In this paper, we propose a hierarchical architecture which assumes a sequence of human action (low-level) can be driven from the human intention (high-level). Based on this, we deal with long-term action anticipation task in egocentric videos. Our framework first extracts this low- and high-level human information over the observed human actions in a video through a Hierarchical Multi-task Multi-Layer Perceptrons Mixer (H3M). Then, we constrain the uncertainty of the future through an Intention-Conditioned Variational Auto-Encoder (I-CVAE) that generates multiple stable predictions of the next actions that the observed human might perform. By leveraging human intention as high-level information, we claim that our model is able to anticipate more time-consistent actions in the long-term, thus improving the results over the baseline in Ego4D dataset. This work results in the state-of-the-art for Long-Term Anticipation (LTA) task in Ego4D by providing more plausible anticipated sequences, improving the anticipation scores of nouns and actions. Our work ranked first in both CVPR@2022 and ECCV@2022 Ego4D LTA Challenge. © 2022, CC BY.

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：