检索结果-内蒙古大学图书馆

Subject Recognition in Chinese Sentences for Chatbots 8th

学校读者我要写书评

暂无评论

Subject Recognition in Chinese Sentences for Chatbots

8th CCF International Conference on Natural Language Processing and Chinese Computing, NLPCC 2019

作者： Li, Fangyuan Wei, Huanhuan Hao, Qiangda Zeng, Ruihong Shao, Hao Chen, Wenliang Gowild Robotics Co. Ltd. Shenzhen China School of Computer Science and Technology Soochow University Suzhou China

ISBN: (纸本)9783030322359

Subject (In this paper, subject means " /zhu ti" in Chinese, while we use "grammatical subject" to denote traditional " /zhu yu" in Chinese.) recognition plays a significant role in the conversation with a Chatbot. The misclassification of the subject of a sentence leads to the misjudgment of the intention recognition. In this paper, we build a new dataset for subject recognition and propose several systems based on pre-trained language models. We first design annotation guidelines for human-chatbot conversational data, and hire annotators to build a new dataset according to the guidelines. Then, classification methods based on deep neural network are proposed. Finally, extensive experiments are conducted to testify the performance of different algorithms. The results show that our method achieves 88.5% F:1 in the task of subject recognition. We also compare our systems with three other Chatbot systems and find ours perform the best. © 2019, Springer Nature Switzerland AG.

关键词： Deep neural networks

Towards end-to-end deep learning for autonomous racing: On data collection and a unified architecture for steering and throttle prediction

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wadekar, Shakti N. Schwartz, Benjamin J. Kannan, Shyam S. Mar, Manuel Manna, Rohan Kumar Chellapandi, Vishnu Gonzalez, Daniel J. Gamal, Aly El School of Electrical and Computer Engineering Purdue University West LafayetteIN47907 United States Computer Information Technology Polytechnic Institute Purdue University West LafayetteIN47907 United States Robotics Research Center Department of Electrical Engineering and Computer Science United States Military Academy West PointNY10996 United States

Deep Neural Networks (DNNs) which are trained end-to-end have been successfully applied to solve complex problems that we have not been able to solve in past decades. Autonomous driving is one of the most complex problems which is yet to be completely solved and autonomous racing adds more complexity and exciting challenges to this problem. Towards the challenge of applying end-to-end learning to autonomous racing, this paper shows results on two aspects: (1) Analyzing the relationship between the driving data used for training and the maximum speed at which the DNN can be successfully applied for predicting steering angle, (2) Neural network architecture and training methodology for learning steering and throttle without any feedback or recurrent connections. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

Sparse Bayesian Deep Learning for Dynamic System Identification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhou, Hongpeng Ibrahim, Chahine Zheng, Wei Xing Pan, Wei Department of Cognitive Robotics Delft University of Technology Delft2628 CD Netherlands School of Computer Data and Mathematical Sciences Western Sydney University SydneyNSW2751 Australia Department of Computer Science The University of Manchester ManchesterM13 9PL United Kingdom

This paper proposes a sparse Bayesian treatment of deep neural networks (DNNs) for system identification. Although DNNs show impressive approximation ability in various fields, several challenges still exist for system identification problems. First, DNNs are known to be too complex that they can easily overfit the training data. Second, the selection of the input regressors for system identification is nontrivial. Third, uncertainty quantification of the model parameters and predictions are necessary. The proposed Bayesian approach offers a principled way to alleviate the above challenges by marginal likelihood/model evidence approximation and structured group sparsity-inducing priors construction. The identification algorithm is derived as an iterative regularised optimisation procedure that can be solved as efficiently as training typical DNNs. Remarkably, an efficient and recursive Hessian calculation method for each layer of DNNs is developed, turning the intractable training/optimisation process into a tractable one. Furthermore, a practical calculation approach based on the Monte-Carlo integration method is derived to quantify the uncertainty of the parameters and predictions. The effectiveness of the proposed Bayesian approach is demonstrated on several linear and nonlinear system identification benchmarks by achieving good and competitive simulation accuracy. © 2021, CC BY-NC-SA.

关键词： Deep neural networks

Wireless-Powered UAV assisted Communication System in Nakagami-m Fading Channels 17

学校读者我要写书评

暂无评论

Wireless-Powered UAV assisted Communication System in Nakaga...

17th IEEE Annual Consumer Communications and Networking Conference, CCNC 2020

作者： Ponnimbaduge Perera, Tharindu D. Jayakody, Dushantha Nalin K. Garg, Sahil Kumar, Neeraj Cheng, Ling School of Computer Science and Robotics National Research Tomsk Polytechnic University Russia School of Postgraduate Studies Research Sri Lanka Technological Campus Padukka Sri Lanka Ecole de Technologie Supérieure Electrical Engineering Department MontrealQCH3C 1K3 Canada Thapar Institute of Engineering and Technology Department of Computer Science and Engineering India School of Electrical and Information Engineering University of the Witwatersrand South Africa

ISBN: (纸本)9781728138930

Recently, the use of unmanned aerial vehicles (UAVs) as a relay node has been envisaged as an enabling technology in the upcoming wireless communication era. Thus, in this paper, we consider a full-duplex (FD) cooperative communication system with a source and a destination, where UAV serves as a mobile relay. Here, the transmission power cost is debited to energy harvested using simultaneous wireless information and power transfer (SWIPT) and self-interference energy harvesting (EH) via power-splitting (PS) protocol. In poor channel conditions, UAV uses a soft angular modulation scheme to perceive the soft information. In this proposed system, we present the outage probability over the Nakagami-m fading channels. A closed-form solution for the outage probability is derived. In addition, we formulate an optimization problem to minimize end-to-end outage probability subject of the UAV's power profile. The KKT conditions have been used to obtain a closed-form solution of the proposed optimization problem. Finally, numerical results are provided to evaluate the proposed system under various setups. © 2020 IEEE.

关键词： Cooperative communication

A Bipolar Myoelectric Sensor-Enabled Human-Machine Interface Based On Spinal Module Activations

学校读者我要写书评

暂无评论

A Bipolar Myoelectric Sensor-Enabled Human-Machine Interface...

IEEE International Conference on robotics and Automation (ICRA)

作者： Chunzhi Yi Feng Jiang Guangming Lu Chifu Yang Zhen Ding Jianfei Zhu Jie Liu State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin Heilongjiang China School of Computer Science and Technology Harbin Institute of Technology Harbin Heilongjiang China Pengcheng Laboratory Shenzhen Guangdong China Nanjing Jinling Hospital Clinical School Medical College Nanjing University Nanjing Jiangsu China AI Research Institute Harbin Institute of Technology Shenzhen Guangdong China

The surface electromyography (sEMG) signal-based human-machine interface (HMI) has been widely used for various scenarios of physical human-robot interaction. However, current HMIs based on bipolar myoelectric sensors are hindered by the limitations of global sEMG features, which are prone to variability and delay. In this letter, we define a HMI that takes advantage of the underlying neural information of spinal module activations from bipolar sEMG signals, inspired by recent findings of neural codes. Firstly, the spinal module activations are identified by the spiking trains of the muscle synergies extracted from bipolar sEMG signals. Secondly, we extract the information encoded in both firing rates and spike timings of the spinal module activation in a population coding manner, which follows the information encoding principle of neurons. Thirdly, we map the series of spinal module activations into gait phases, locomotion modes, joint moment and human identity in order to experimentally reveal the physiological information contained in the spinal module activations. The contained information and the benefit of our design are demonstrated and experimentally explained by the presented results and comparisons with the traditionally used global sEMG features. The proposed bipolar myoelectric sensor-enabled human-machine interface could contribute to various scenarios of physical human-robot interaction.

关键词： Sociology Neurons Human-robot interaction Sensor phenomena and characterization Muscles Robot sensing systems Encoding

Multi-camera Torso Pose Estimation using Graph Neural Networks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Rodriguez-Criado, Daniel Bachiller, Pilar Bustos, Pablo Vogiatzis, George Manso, Luis J. School of Engineering and Applied Science Computer Science Department Aston University United Kingdom Robotics and Artificial Vision Laboratory Caceres School of Technology Universidad de Extremadura Spain

Estimating the location and orientation of humans is an essential skill for service and assistive robots. To achieve a reliable estimation in a wide area such as an apartment, multiple RGBD cameras are frequently used. Firstly, these setups are relatively expensive. Secondly, they seldom perform an effective data fusion using the multiple camera sources at an early stage of the processing pipeline. Occlusions and partial views make this second point very relevant in these scenarios. The proposal presented in this paper makes use of graph neural networks to merge the information acquired from multiple camera sources, achieving a mean absolute error below 125mm for the location and 10◦ for the orientation using low-resolution RGB images. The experiments, conducted in an apartment with three cameras, benchmarked two different graph neural network implementations and a third architecture based on fully connected layers. The software used has been released as open-source in a public repository1. Copyright © 2020, The Authors. All rights reserved.

关键词： Data fusion

A Bottom-up Paradigm for Traffic Scene Graph Representation 2020

学校读者我要写书评

暂无评论

A Bottom-up Paradigm for Traffic Scene Graph Representation

Proceedings of the 2020 9th International Conference on Computing and Pattern Recognition

作者： Zhixuan Zhang Chi Zhang Yuehu Liu Yuanqi Su Ping Li Jinzi Zheng School of Software Engineering Xi'an Jiaotong University Xi'an China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China and Shaanxi Key Lab of Digital Technology and Intelligent Systems Xi'an China School of Computer Science and Technology Xi'an Jiaotong University Xi'an China China Academy of Railway Sciences Corporation Limited Beijing China

ISBN: (纸本)9781450387835

With increasing hardware computing power and model capacity, visual tasks for scene cognitive understanding have attracted more attention, such as visual relationships inference. The scene graph representation formed by a coupling of objects, attributes and relationships nodes displayed by different modalities of information, including original image, foreground things, background stuff and scene attributes, strongly promotes the progress of research area. In this paper, we address the scene graph representation of traffic scenarios for autonomous driving. It should be noted that the universal representation are the specific needs of cognitive understanding of traffic scenes: on the one hand, there is a lack of fine-grained description of key objects and attributes; on the other hand, there are redundant descriptions of objects and relationships. To tackle these problems, we take advantage of the fine-grained instance-level annotation of the traffic scene, proposing a bottom-up representation paradigm. It makes full use of the hierarchical structure of the traffic scene and the sparsity of element classes. In addition, on the basis of the existing methods, we optimize the relationship list of traffic scene graph representation. Moreover, we improve the scene graph annotation methods, proposing a "ground-vision joint location method" to better describe the spatially-distributed visual knowledge. The case analysis showed that compared with existing methods, our paradigm for scene graph can represent more abundant traffic scene information.

关键词： visual relationship description traffic knowledge representation autonomous driving Scene graph

Estimating motor symptom presence and severity in Parkinson’s disease from wrist accelerometer time series using ROCKET and InceptionTime

学校读者我要写书评

暂无评论

Scientific Reports 2025年第1期15卷 1-15页

作者： Donié, Cedric Das, Neha Endo, Satoshi Hirche, Sandra TUM School of Computation Information and Technology Department of Computer Engineering Chair of Information-oriented Control Technical University of Munich Munich Germany Munich Data Science Institute (MDSI) Munich Germany Munich Institute of Robotics and Machine Intelligence (MIRMI) Munich Germany

Parkinson’s disease (PD) is a neurodegenerative condition characterized by frequently changing motor symptoms, necessitating continuous symptom monitoring for more targeted treatment. Classical time series classification and deep learning techniques have demonstrated limited efficacy in monitoring PD symptoms using wearable accelerometer data due to complex PD movement patterns and the small size of available datasets. We investigate InceptionTime and RandOm Convolutional KErnel Transform (ROCKET) as they are promising for PD symptom monitoring. InceptionTime’s high learning capacity is well-suited to modeling complex movement patterns, while ROCKET is suited to small datasets. With random search methodology, we identify the highest-scoring InceptionTime architecture and compare its performance to ROCKET with a ridge classifier and a multi-layer perceptron on wrist motion data from PD patients. Our findings indicate that all approaches can learn to estimate tremor severity and bradykinesia presence with moderate performance but encounter challenges in detecting dyskinesia. Among the presented approaches, ROCKET demonstrates higher scores in identifying dyskinesia, whereas InceptionTime exhibits slightly better performance in tremor and bradykinesia estimation. Notably, both methods outperform the multi-layer perceptron. In conclusion, InceptionTime can classify complex wrist motion time series and holds potential for continuous symptom monitoring in PD with further development. © The Author(s) 2025.

关键词： Accelerometer Deep learning IMU InceptionTime Machine learning Parkinson’s disease ROCKET Time series classification

Lyapunov-based reinforcement learning state estimator

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Hu, Liang Wu, Chengwei Pan, Wei School of Computer Science and Electronic Engineering University of Essex United Kingdom School of Astronautics Harbin Institute of Technology China Department of Cognitive Robotics Delft University of Technology Netherlands

In this paper, we consider the state estimation problem for nonlinear stochastic discrete-time systems. We combine Lyapunov’s method in control theory and deep reinforcement learning to design the state estimator. We theoretically prove the convergence of the bounded estimate error solely using the data simulated from the model. An actor-critic reinforcement learning algorithm is proposed to learn the state estimator approximated by a deep neural network. The convergence of the algorithm is analysed. The proposed Lyapunov-based reinforcement learning state estimator is compared with a number of existing nonlinear filtering methods through Monte Carlo simulations, showing its advantage in terms of estimate convergence even under some system uncertainties such as covariance shift in system noise and randomly missing measurements. To the best of our knowledge, this is the first reinforcement learning based nonlinear state estimator with bounded estimate error performance guarantee. Copyright © 2020, The Authors. All rights reserved.

关键词： Nonlinear filtering