检索结果-内蒙古大学图书馆

IEEE international conference on robotics and Automation (ICRA)

作者： Fernando Díaz Ledezma Sami Haddadin Munich School of Robotics and Machine Intelligence Technische Universität München München Germany Potential Conflict of Interest as Shareholder of Franka Emika GmbH

We transform classical robot inertial parameter identification into an online learning problem by integrating state-of-the-art gradient descent techniques and first-order principles from mechanics and differential geometry. Through this, incremental learning of fully physically feasible inertial properties without requiring any prior information is made possible. This is achieved using a version of Riemannian gradient descent equipped with experience replay that guarantees feasible parameter updates at all times during learning. analysis of the method's performance are done on a virtual manipulator focusing on the influence that different measurement setups have on the estimation as well as on parameter feasibility and re-learning. Finally, we present experimental results on a real 7 DoF manipulator and evaluate the quality of the generated inverse dynamics torques and the corresponding model error.

关键词： Geometry Adaptation models Analytical models Sensitivity Parameter estimation Computational modeling Transforms

来源：评论

学校读者我要写书评

暂无评论

Determination of Singularity Occurrence and Characteristic analysis of Dual 6-DOF Manipulator Using Manipulability and Manipulability Ellipsoid 13th

Determination of Singularity Occurrence and Characteristic A...

引用

13th international conference on Intelligent robotics and Applications (ICIRA)

作者： Lee, Jong-Hak Bang, Jin-Uk Lee, Jang-Myung Pusan Natl Univ Dept Elect & Comp Engn 2Busandaehak Ro 63Beon Gil Busan South Korea Pusan Natl Univ Dept Elect Engn 2Busandaehak Ro 63Beon Gil Busan South Korea

ISBN: (纸本)9783030666453;9783030666446

In this paper, we judge whether the singularity occurs among the path of dual 6-DOF manipulator using manipulability and analyze the characteristics in the velocity space of the straight path and alternative path what avoids the singularity using manipulability ellipsoid. To do this, we solved the inverse kinematics of the manipulator and made simulator in MATLAB. In this simulator, the path can be set in advance and change of manipulability and manipulability ellipsoid can be observed. This allows better path to be determined in advance before following it. Experiments has confirmed that singularity occurs in straight path and eigenvalue in the direction of yaw is zero. In addition, the alternative path is identified as an improved path due to the large eigenvalue in the direction of pitch and yaw. Since this result can be used as an indicator for evaluating the agent's state, we intend to apply to reinforcement learning and research to create a singularity avoidance path by the robot itself.

关键词： Manipulator Manipulability Manipulability ellipsoid Path analysis

来源：评论

学校读者我要写书评

暂无评论

Sparse decomposition of pressure pulse wave signal based on time frequency analysis 5

Sparse decomposition of pressure pulse wave signal based on ...

引用

5th international conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)

作者： Jiang, Zhixing Lu, Guangming Zhang, David Harbin Inst Technol Sch Comp Sci & Technol Shenzhen Peoples R China Shenzhen Res Inst Big Data Shenzhen Peoples R China Shenzhen Inst Artificial Intelligence & Robot Soc Shenzhen Peoples R China

ISBN: (纸本)9781728180229

In traditional Chinese medicine (TCM), wrist pulse is of great significance to help doctors in diagnosis. With the development of sensing technology, the computerized wrist pulse analysis has been attracting more attention in modern medicine for its non-invasive and convenient. Considering the TCM pulse diagnosis theory, it is necessary to develop effective feature extraction methods for computerized diagnosis. In this paper, we decompose the pressure pulse waveform of the radial artery to several components by sparse decomposition with Gabor function. In order to better represent the pulse waveform signal, we use an Gabor function based on the characteristics of the pulse waveform to generate a time-frequency dictionary. Compared with the conventional representation methods, the shape of the Gabor function is more variable, which can better represent both the contour and specific peaks. In addition, due to the limitation of the windowing, the Gabor function can reduce the influence on other positions when representing specific position. The feature vector composed of the decomposed components can be used for the computerized pulse signal analysis and disease diagnosis. The experimental results show that the proposed method can exhibit superior performance in distinguishing between the signals collected from patients and healthy individuals.

关键词： Wrist pulse disease diagnosis Gabor function sparse decomposition time-frequency analysis

来源：评论

学校读者我要写书评

暂无评论

Epilepsy Detection using Bi-LSTM with Explainable Artificial intelligence

Epilepsy Detection using Bi-LSTM with Explainable Artificial...

引用

IEEE India conference (INDICON)

作者： Prajakta Rathod Jayendra Bhalodiya Shefali Naik School of Engineering and Applied Science Ahmedabad University Ahmedabad Gujarat India

ISBN: (纸本)9781665452724

Neurological disorder, epilepsy, may represent as abnormal brain activities, causing seizures. Such conditions can be monitored through disturbances in normal Electroencephalogram (EEG) pattern. In literature, researchers have utilised EEG changes in epilepsy patients for automatic seizure detection using machine learning (ML). Particularly, deep learning methods noted promising accuracy in distinguishing normal and abnormal signals caused by epilepsy to classify epileptic and non-epileptic patients. However, explanation of such accuracy and decision steps are warranted for their technical verifications and clinical validations for a potential use in clinics. Explainable artificial intelligence (XAI) plays a key role in explaining such results. In this paper, we proposed a system which uses Bi-LSTM network for classification of normal and abnormal signals caused by epilepsy, and XAI method Layer-wise Relevance Propagation (LRP) to explain the predictions of the network. We implemented LRP in the Bi-LSTM network. LRP method generated relevance vector for test input vector. We reported these relevance values which indicate contribution of each data point of a signal in classification of a signal in particular class. Moreover, we displayed part of input signal, which plays a major role in signal classification, with the classification results. This is the first to use XAI method LRP with Bi-LSTM network to justify the network prediction for seizure detection in epilepsy patients. Such use of XAI method could help neurologists to build up confidence for an informed decision while using deep learning technologies in epilepsy diagnosis.

关键词： Deep learning Neurological diseases Brain Image color analysis Epilepsy pattern classification Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Learning to Walk: Bio-Mimetic Hexapod Locomotion via Reinforcement-Based Spiking Central pattern Generation

引用

IEEE JOURNAL ON EMERGING AND SELECTED TOPICS IN CIRCUITS AND SYSTEMS 2020年第4期10卷 536-545页

作者： Lele, Ashwin Sanjay Fang, Yan Ting, Justin Raychowdhury, Arijit Georgia Inst Technol Sch Elect & Comp Engn Atlanta GA 30313 USA

Online learning for the legged robot locomotion under performance and energy constraints remains to be a challenge. Methods such as stochastic gradient, deep reinforcement learning (RL) have been explored for bipeds, quadrupeds and hexapods. These techniques are computationally intensive and thus difficult to implement on edge computing platforms. These methods are also inefficient in energy consumption and throughput because of their reliance on complex sensors and pre-processing of data. On the other hand, neuromorphic computing paradigms, such as spiking neural networks (SNN), become increasingly favorable in low power computing on edge intelligence. SNN has exhibited the capability of performing reinforcement learning mechanisms with biomimetic spike time-dependent plasticity (STDP) of synapses. However, training a legged robot to walk in the synchronized gait patterns generated by a central pattern generator (CPG) in an SNN framework has not yet been explored. Such a method can combine the efficiency of SNNs with the synchronized locomotion of CPG based systems - providing breakthrough performance improvement of end-to-end learning in mobile robotics. In this paper, we propose a reinforcement based stochastic learning technique for training a spiking CPG for a hexapod robot which learns to walk using bio-inspired tripod gait without prior knowledge. The whole system is implemented on a lightweight raspberry pi platform with integrated sensors. Our method opens new opportunities for online learning with limited edge computing resources.

关键词： Neuroplasticity Legged locomotion Real-time systems Closed loop systems Neural networks Biomimetics Reinforcement learning Central pattern generator spiking neural networks spike time-dependent plasticity stochastic reinforcement-based STDP robotic locomotion

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of Approaches to Depth Map Generation for Robot Navigation 5th

Comparative Analysis of Approaches to Depth Map Generation f...

引用

5th international conference on Interactive Collaborative robotics (ICR)

作者： Rubtsova, Julia Iakovlev, Roman Russian Acad Sci Lab Autonomous Robot Syst St Petersburg Fed Res Ctr Russian Acad Sci SPC RA St Petersburg Inst Informat & Automat 39 14th Line St Petersburg 199178 Russia

ISBN: (纸本)9783030603373;9783030603366

This paper considers approaches, which implement depth map reconstruction using stereo pair, as well deep neural network (DNN) - based approaches. Comparative evaluation of these approaches for different classes of images is performed, exampled by specific solutions;whereby the images in these classes differ in their features, distance from the camera viewport, as well scene luminosity level. Averaged frame processing time in video sequence was, in terms of NN-approach, 0.094 s, and in the stereo pair-based approach - 0.105 s. Upon the results of the performed experimental evaluation, suggestions are proposed concerning the criteria, which define preference of the approaches in question in depth map composition, depending on the conditions in the scene.

关键词： Computer vision Depth map Deep learning Deep neural networks Stereo pair

来源：评论

学校读者我要写书评

暂无评论

Research on Lower limb Movement pattern Recognition Method Based on ReliefF-KPCA-SVM

Research on Lower limb Movement Pattern Recognition Method B...

引用

IEEE international conference on robotics and Biomimetics

作者： Jianhua Zhang Junding Guo Hao Wang Kexiang Li Yan Zhao School of Mechanical Engineering Hebei University of Technology China Hebei University of Technology China

ISBN: (纸本)9781665405362

Faced with the complexity of traditional multisensor information fusion and the low recognition rate of lower limb motion pattern, a lower limb motion pattern recognition method based on ReliefF(feature weighting algorithms) and KPCA(kernel principle component analysis) combined with SVM(support vector machine) is proposed. Firstly, IMU and plantar pressure were selected as the information sources for gait pattern recognition, and the time domain and energy features (mean value, mean square error, extreme value, correlation coefficient and wavelet entropy) of the collected lower limb motion information were selected for ReliefF feature selection. Secondly, KPCA feature dimensionality reduction is performed on the selected features to remove the redundant information, and the eigenvalues can reflect the characteristics of motion mode are obtained. Finally, SVM was used to classify the feature vectors of lower limb motion patterns, and 10 movement patterns were identified, such as walking, upstairs, downstairs, uphill, downhill, jogging, cycling, squatting, sitting and standing. The recognition results of this paper are compared with BP neural network and PNN probabilistic neural network, which verifies the feasibility and practicability of this method.

关键词： Support vector machines Legged locomotion Wavelet domain Neural networks Exoskeletons Mean square error methods Probabilistic logic

来源：评论

学校读者我要写书评

暂无评论

Crime prediction: pattern recognition and prediction of collusive bidding 2

Crime prediction: Pattern recognition and prediction of coll...

引用

2021 2nd international conference on Internet of Things, Artificial intelligence and Mechanical Automation, IoTAIMA 2021

作者： Zhai, Yiming Cheng, Junqing Ding, Ning Fan, Zhenyu Lu, Yang Public Security Behavioral Science Lab People's Public Security University of China Beijing China College of Investigation People's Public Security University of China Beijing China

Bidding is an effective means to promote fair competition in the market and optimize the allocation of social resources. However, with the increasing incidence of bid-rigging crimes, public resource regulatory agencies and public security agencies are facing new challenges. On the premise of fully studying the current trend of China's domestic collusive bidding crimes, this paper summarized the abnormal characteristics of four categories of companies suspected of bid rigging, and selected seven representative subcategories of data based on actual conditions, and set thresholds for these data. Then machine learning methods were utilized to build a pre-warning model for collusion bidding. The results show that the use of machine learning methods to predict the bid collusion can achieve a maximum accuracy of 95%. The research can not only improve the early warning, monitoring, analysis and judgment capabilities of the economic crime investigation department, but ensure the benign operation of bidding, and protect the sustained and rapid development of the social economy. © Published under licence by IOP Publishing Ltd.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Spatial Explicit Evaluation of Land Use Sustainability Based on Grid analysis—A Case Study of the Bohai Rim 1

引用

2nd international conference on Spatial Data and intelligence, SpatialDI 2021

作者： Pang, Yu Ju, Hongrun Lu, Shunkang School of Tourism and Geography Science Qingdao University Qingdao266071 China Basic Teaching Center Ocean University of China Qingdao266100 China

ISBN: (数字)9783030854621

ISBN: (纸本)9783030854614

Identifying the land use sustainability at an explicit spatial level in large areas is critical for optimizing the land use. The evaluation of sustainable land use generally takes the administrative units at the provincial, prefecture, or county level as the spatial scale, which ignore the spatial variation within the administrative units. This paper aims to put forward a novel evaluation method on sustainable land use evaluation and evaluate the land use sustainability at a grid level of 5 km in Bohai Rim of China. This paper first established an index system of sustainable land use evaluation frame with 13 indicators in four criterion levels: ecology, economy, society, and spatial pattern. Then, the 13 indicators were expressed at 5 km grids level. At last, the land use sustainability was evaluated of each grids based on the spatial principal component analysis. The results showed that the ecological environment in the Bohai Rim has the greatest impact on the level of sustainable land use. The high level of sustainable land use is generally distributed in the northwest and northeast in Bohai Rim, and the low level of sustainability is concentrated in the southwest of the Bohai Rim. This paper proposed a novel method to evaluate of the land use sustainability at a spatial explicit level. The method could offer more spatial information of sustainable land use to help government propose more efficient policies regarding improving land use sustainability. © 2021, Springer Nature Switzerland AG.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

4th international conference on Innovative Technologies and Learning, ICITL 2021

4th International Conference on Innovative Technologies and ...

引用

4th international conference on Innovative Technologies and Learning, ICITL 2021

ISBN: (纸本)9783030915391

The proceedings contain 61 papers. The special focus in this conference is on Innovative Technologies and Learning. The topics include: A Study of Learner’s Scientific Thinking Using Constructivist Virtual Learning Environment for Grade 11 Students;Regarding the Virtual Reality Environment Design and Evaluation Based on STEAM Learning;Using STEAM-6E Model in AR/VR Maker Education Teaching Activities to Improve High School Students’ Learning Motivation and Learning Activity Satisfaction;The Use of E-learning Tools in a Basic Logic Course During the COVID-19 Lockdown;improve University Humanities Students’ Problem-Solving Ability Through Computational Thinking Training;the Development of a Computational Thinking Learning Package that Integrates a Learning Experience Design for Grade K;development of Online Learning to Enhancing Computational Thinking for High School Students;exploring the Usability of Web-Based Java Compiler as a Learning Tool;young Kids’ Basic Computational Thinking: An analysis on Educational robotics Without Computer;Amending Dynamic Capability Theory for Information Systems Research on the Reskilling of Coal Miners in an AI-Driven Era;the Validation of Constructivist Web-Based Learning Environment Model to Enhance Creativity Thinking for Undergraduate Student with Integration of Pedagogy and Neuroscience;resource Designing Framework of Constructivist Web-Based Learning Environment to Enhance the Problem-Solving for Robot Programming in Secondary Grade 3;AHP4Edu: An AHP-Based Assessment Model for Learning Effectiveness of Education;a Designing Framework for Flipped Classroom Learning Environment Model Combined with Augmented Reality to Enhance Creative Thinking in Product Design for High School Students;Using Design patterns to Teach Conceptual Entity Relationship (ER) Data Modelling;digital Application Literacy.

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：