检索结果-内蒙古大学图书馆

Machine Learning Algorithms for Natural Language Processing Tasks: A Case of COVID-19 Twitter data (Thailand)

学校读者我要写书评

暂无评论

Machine Learning Algorithms for Natural Language Processing ...

International Conference on Computational Science and Computational Intelligence (CSCI)

作者： Kunyanuth Kularbphettong Rujijan Vichivanives Pannawat Kanjanaprakarn Jaruwan Chutrtong Nareenart Ruksuntorn Computer Science Program Suan Sunandha Rajabhat University Bangkok Thailand Faculty of Science and Technology Suan Sunandha Rajabhat University Bangkok Thailand Robotics Engineering program Faculty of Industrial Technology Suan Sunandha Rajabhat University Bangkok Thailand

This paper presents the use of natural language processing for the problem of information extraction and sentiment analysis. The dataset is from Twitter that has the information of people mentioning about COVID-19, this study has two tasks: (i) classification approach for information extraction task and (ii) deep learning approach for sentiment analysis task. In information extraction task, the data was gathered from twitter that related to COVID-19 information, and the sequence labelling method applied to classify text before giving it to classification algorithms (K-NN, Naïve Bayes, Decision Tree, Random Forest, and SVM). In sentiment analysis task, data was classified by convert the word into index and using word embedding, then to process deep learning algorithm (Bi-directional GRU). The accuracy of two tasks are 98% and 79% respectively.

关键词：

Computational Analysis of Mechanical Interactions between a Soft Robotic Device and a Skin-Muscle Phantom for Mechanotherapy

学校读者我要写书评

暂无评论

Computational Analysis of Mechanical Interactions between a ...

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Victor Ticllacuri Renato Mio Biomedical Engineering Program PUCP-UPCH Lima Perú Laboratory of Biomechanics and Applied Robotics Pontificia Universidad Catolica del Peru Lima Perú Laboratory of Biomedical Engineering Universidad Peruana Cayetano Heredia Lima Perú Chair of Digital Health With a Focus on Data Science University of Bayreuth Germany

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Studying the soft robot-tissue mechanical interaction in muscle stimulation devices poses a significant challenge due to the complex behavior of the materials involved. To advance this field, this paper models computationally three types of soft elastomeric actuators designed to perform deep cyclic compression stimuli on human soft tissues for muscle rehabilitation by mechanotherapy. The analysis focuses on the interaction between a phantom representing transversely isotropic muscle and homogeneous skin, with a soft robotic device comprised of a hyperelastic actuator and a rigid support. Results from deformation, stress-strain and surface pressure analysis demonstrate efficient actuation, suggesting deep and focused stimulation on the muscle, while actuators exhibit reliable safety factors and load distribution, implying longer operational life. This lightweight and compact soft robotic device is suitable for integration into a wearable suit for targeted muscle groups stimulation in the lower limbs. Furthermore, this computational approach represents a significant advance in the biomechanical study of soft robot-human tissues interaction, with potential for generalization in similar biomedical device applications. Keywords—Soft robotics, Mechanotherapy, Transversely Isotropic Muscle, Human-Robot interaction.

关键词： Analytical models Actuators Computational modeling Biological system modeling Biological tissues Phantoms Muscles Soft robotics Skin Load modeling

A Design for Improvement of Visual SLAM in Dynamic Environments Using Feature-Point Removal of Moving Persons

学校读者我要写书评

暂无评论

A Design for Improvement of Visual SLAM in Dynamic Environme...

International Automatic Control Conference

作者： Kai-Tai Song Ching-Hao Meng Institute of Electrical and Control Engineering College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan Graduate Degree Program of Robotics College of Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan

This paper presents a design to improve the robustness of visual SLAM(vSLAM). A processing step of feature-removal is added to the tracking thread of the conventional ORB-SLAM2 algorithm to improve the localization accuracy of a mobile robot in an environment with moving persons. Instance segmentation and motion tracking are intergrated to identify motion state of people in an image. ORB feature points belonging to moving persons are removed for further processing of the vSLAM pipeline. The advantage of this method is that the vSLAM can remove feature points of moving people, while retain those belonging to static people in the environment, which improves the accuracy of robot pose estimation. The improved ORB-SLAM2 algorithm has been implemented in a NVIDIA Xavier embedded system, which is integrated to a mobile robot. In practical robot navigation experiments, the average positioning error of the proposed method is within 4cm for 22.4m travel distance. Compared with conventional ORB-SLAM2, the average accuracy of our vSLAM method improves 97% in a dynamic environment with moving people.

关键词：

Experimentally Probing Non-Hermitian Spectral Transition and Eigenstate Skewness

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhong, Jia-Xin Kim, Jeewoo Chen, Kai Lu, Jing Ding, Kun Jing, Yun Graduate Program in Acoustics The Pennsylvania State University University ParkPA16802 United States Key Laboratory of Modern Acoustics Institute of Acoustics Nanjing University Nanjing210093 China Fudan University Shanghai200438 China NJU-Horizon Intelligent Audio Lab Horizon Robotics Beijing100094 China

Non-Hermitian (NH) systems exhibit intricate spectral topology arising from complex-valued eigenenergies, with positive/negative imaginary parts representing gain/loss. Unlike the orthogonal eigenstates of Hermitian systems, NH systems feature left and right eigenstates that form a biorthogonal basis and can differ significantly, showcasing pronounced skewness between them. These characteristics give rise to unique properties absent in Hermitian systems, such as the NH skin effect and ultra spectral sensitivity. However, conventional experimental techniques are inadequate for directly measuring the complex-valued spectra and left and right eigenstates—key elements for enhancing our knowledge of NH physics. This challenge is particularly acute in higher-dimensional NH systems, where the spectra and eigenstates are highly sensitive to macroscopic shapes, lattice geometry, and boundary conditions, posing greater experimental demands compared to one-dimensional systems. Here, we present a Green’s function-based method that enables the direct measurement and characterization of both complex-valued energy spectra and the left and right eigenstates in arbitrary NH lattices. Using active acoustic crystals as the experimental platform, we observe spectral transitions and eigenstate skewness in two-dimensional NH lattices under both nonreciprocal and reciprocal conditions, with varied geometries and boundary conditions. Our approach renders complex spectral topology and left eigenstates experimentally accessible and practically meaningful, providing new insights into these quantities. The results not only confirm recent theoretical predictions of higher-dimensional NH systems but also establish a universal and versatile framework for investigating complex spectral properties and NH dynamics across a wide range of physical platforms. Copyright © 2025, The Authors. All rights reserved.

关键词： Topology

AV Navigation in 3D Urban Environments with Curriculum-based Deep Reinforcement Learning

学校读者我要写书评

暂无评论

AV Navigation in 3D Urban Environments with Curriculum-based...

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Kevin Braathen de Carvalho Iure Rosa L. de Oliveira Alexandre S. Brandão Department of Electrical Engineering Graduate Program in Computer Science Nucleus of Specialization in Robotics Universidade Federal de Viçosa Viçosa MG Brazil Department of Electrical Engineering Federal University of Viçosa Viçosa MG Brazil

Unmanned Aerial Vehicles (UAVs) are widely used in various applications, from inspection and surveillance to transportation and delivery. Navigating UAVs in complex 3D environments is a challenging task that requires robust and efficient decision-making algorithms. This paper presents a novel approach to UAV navigation in 3D environments using a Curriculum-based Deep Reinforcement Learning (DRL) approach. The proposed method utilizes a deep neural network to model the UAV’s decision-making process and to learn a mapping from the state space to the action space. The learning process is guided by a reinforcement signal that reflects the performance of the UAV in terms of reaching its target while avoiding obstacles and with energy efficiency. Simulation results show that the proposed method has a positive trade off when compared to the baseline algorithm. The proposed method was able to perform well in environments with a state space size of 22 millions, allowing the usage in big environments or in maps with high resolution. The results demonstrate the potential of DRL for enabling UAVs to operate effectively in complex environments.

关键词：

Mathematical Modeling and Characterization of a Wearable Soft Robotic Device for Muscle Mechanotherapy

学校读者我要写书评

暂无评论

Mathematical Modeling and Characterization of a Wearable Sof...

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Victor Ticllacuri Renato Mio Biomedical Engineering Program PUCP-UPCH Lima Perú Laboratory of Biomechanics and Applied Robotics Pontificia Universidad Catolica del Peru Lima Perú Laboratory of Biomedical Engineering Universidad Peruana Cayetano Heredia Lima Perú Chair of Digital Health with a Focus on Data Science University of Bayreuth Germany

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Treatments of disuse-induced muscle atrophy entail unmet clinical needs due to the lack of medical devices capable of mimicking physicians manual therapies. Therefore, in this paper we develop and model a wearable soft pneumatic elastomeric actuator to perform deep cyclic compression stimuli on human soft tissues for muscle rehabilitation by mechanotherapy. Static and dynamic characterization of the prototype demonstrate a 2.5 mm active deformation at 100 kPa with 600 mm 3 /s and a 5 Hz bandwidth. We estimate the transfer function of the experimentally acquired pressure, flow and deformation signals, processed by a Gaussian kernel-based approach. Our mathematical model accurately describes the actuator behavior and enables to extract its mechanical parameters. Then, through computational simulations, we illustrate its efficacy in emulating multiple complex bio-inspired movements. Our proposed methodology aims to improve the control efficiency in wearable soft robotics for muscle atrophy treatment.

关键词： Atrophy Actuators Deformation Computational modeling Biological system modeling Transfer functions Prototypes Muscles Soft robotics Mathematical models

Self-propulsion via slipping: frictional swimming in multi-legged locomotors

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chong, Baxi He, Juntao Li, Shengkai Erickson, Eva Diaz, Kelimar Wang, Tianyu Soto, Daniel Goldman, Daniel I. Interdisciplinary Graduate Program in Quantitative Biosciences United States School of Physics United States Institute for Robotics and Intelligent Machines Georgia Institute of Technology AtlantaGA United States

Locomotion is typically studied either in continuous media where bodies and legs experience forces generated by the flowing medium, or on solid substrates dominated by friction. In the former, centralized coordination is believed to facilitate appropriate slipping through the medium for propulsion. In the latter, slip is often assumed minimal and thus avoided via decentralized controls. We discover in laboratory experiments that terrestrial locomotion of a meter scale multi-segmented/legged robophysical model resembles undulatory fluid swimming. Experiments varying waves of limb stepping and body bending reveal how these parameters result in effective terrestrial locomotion despite seemingly ineffective isotropic frictional contacts. Dissipation dominates over inertial effects in this macroscopic-scaled regime, resulting in essentially geometric locomotion akin to microscopic-scale swimming. Theoretical analysis demonstrates that the high-dimensional multi-segmented/legged dynamics can be simplified to a centralized low-dimensional model, which reveals an effective Resistive Force Theory with an acquired viscous drag anisotropy. We extend our low-dimensional, geometric analysis to illustrate how body undulation can aid performance in non-flat obstacle-rich terrains and also use the scheme to quantitatively model how body undulation affects performance of biological centipede locomotion (the desert centipede S. polymorpha) moving at relatively high speeds (∼ 0.5 body lengths/sec). Our results could facilitate control of multilegged robots in complex terradynamic scenarios. © 2022, CC BY.

关键词： Friction

HeRo 2.0: A Low-Cost Robot for Swarm robotics Research

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Rezeck, Paulo Azpúrua, Héctor Corrêa, Maurício F.S. Chaimowicz, Luiz Graduate Program in Computer Science Computer Vision and Robotics Laboratory Department of Computer Science Universidade Federal de Minas Gerais Brazil Instituto Tecnológico Vale MG Ouro Preto Brazil Vision and Robotics Laboratory Department of Computer Science Universidade Federal de Minas Gerais Brazil Computer Vision and Robotics Laboratory Department of Computer Science Universidade Federal de Minas Gerais Brazil

The current state of electronic component miniaturization coupled with the increasing efficiency in hardware and software allow the development of smaller and compact robotic systems. The convenience of using these small, simple, yet capable robots has gathered the research community's attention towards practical applications of swarm robotics. This paper presents the design of a novel platform for swarm robotics applications that is low cost, easy to assemble using off-the-shelf components, and deeply integrated with the most used robotic framework available today: ROS (Robot Operating System). The robotic platform is entirely open, composed of a 3D printed body and open-source software. We describe its architecture, present its main features, and evaluate its functionalities executing experiments using a couple of robots. Results demonstrate that the proposed mobile robot is very effective given its small size and reduced cost, being suitable for swarm robotics research and education. © 2022, CC BY.

关键词： Swarm intelligence

Distributed Certifiably Correct Range-Aided SLAM

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Thoms, Alexander Papalia, Alan Velasquez, Jared Rosen, David M. Narasimhan, Sriram Sensing and Robotics for Infrastructure Laboratory University of California Los Angeles Los Angeles United States The Massachusetts Institute of Technology The MIT-WHOI Joint Program in Oceanography/Applied Ocean Science & Engineering Woods Hole CambridgeMA United States Robust Autonomy Lab Northeastern University BostonMA United States

Reliable simultaneous localization and mapping (SLAM) algorithms are necessary for safety-critical autonomous navigation. In the communication-constrained multi-agent setting, navigation systems increasingly use point-to-point range sensors as they afford measurements with low bandwidth requirements and known data association. The state estimation problem for these systems takes the form of range-aided (RA) SLAM. However, distributed algorithms for solving the RA-SLAM problem lack formal guarantees on the quality of the returned estimate. To this end, we present the first distributed algorithm for RA-SLAM that can efficiently recover certifiably globally optimal solutions. Our algorithm, distributed certifiably correct RA-SLAM (DCORA), achieves this via the Riemannian Staircase method, where computational procedures developed for distributed certifiably correct pose graph optimization are generalized to the RA-SLAM problem. We demonstrate DCORA’s efficacy on real-world multi-agent datasets by achieving absolute trajectory errors comparable to those of a state-of-the-art centralized certifiably correct RA-SLAM algorithm. Additionally, we perform a parametric study on the structure of the RA-SLAM problem using synthetic data, revealing how common parameters affect DCORA’s performance. Copyright © 2025, The Authors. All rights reserved.

关键词： Navigation systems