检索结果-内蒙古大学图书馆

Correction: Analysis of the effects of acoustic levitation to simulate the microgravity environment on the development of early zebrafish embryos

学校读者我要写书评

暂无评论

RSC advances 2021年第7期11卷 3891页

作者： Li Li Ning Gu Huijuan Dong Bingsheng Li Kenneth T V Grattan School of Life Sciences and Technology Harbin Institute of Technology Harbin 150080 China. State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin 150080 China dhj@***. State Key Laboratory of Urban Water Resource and Environment Harbin Institute of Technology Harbin 150090 China. Key Laboratory of UV Light Emitting Materials and Technology Under Ministry of Education Northeast Normal University Changchun 130024 China libs@***. School of Mathematics Computer Science and Engineering City University of London London EC1V 0HB UK.

[This corrects the article DOI: 10.1039/D0RA07344J.].

关键词：

Accurate Object Recognition for Unmanned Aerial Vehicle Electric Power Inspection using an Improved YOLOv2 Algorithm

学校读者我要写书评

暂无评论

Accurate Object Recognition for Unmanned Aerial Vehicle Elec...

IEEE International Conference on Data science in Cyberspace (DSC)

作者： Qiang Chen Yunyuan Gao Yun Peng Jianhai Zhang Ke Sun Intelligent Control & Robotics Institute Hangzhou Dianzi University Hangzhou China Hangzhou Dianzi University Hangzhou China Department of Biomedical Engineering University of Houston Houston United States School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Hangzhou Chuangjiang Information Technology Co. Ltd. Hangzhou China

With the growing application of Unmanned Aerial Vehicle (UAV) in the electric power inspection, there is an increasing demand for accurate recognition of power tower components from a large number of pictures and videos. Traditional machine learning methods require feature extraction of, such as edge, color, texture, etc., are not suitable for the complex scene of the UAV electric power inspection. The end-to-end object detection algorithm YOLOv2, offers overall high recognition accuracy and speed, but is less so in recognizing small targets . In this study, the YOLOv2 was improved by: 1)adding an additional passthrough layer to the original network to fuse more fine-grained features to improve the recognition capability for small targets, and 2) removing the redundant convolutional layers and reducing the number of the filters in the middle convolutional layers to simplify the network structure. The datasets are from Multi-rotor UAV inspection of high voltage transmission lines. Three types of power tower components including the tower, tower base, and signs are selected as recognition targets. Results showed that the mean average precision (mAP) of the improved model for three types of target recognition was increased to 98.19%, higher than that of the original one, and the recognition speed was increased by 35%.

关键词： Conferences Data science Cyberspace

Variable population memetic search: A case study on the critical node problem

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhou, Yangming Hao, Jin-Kao Fu, Zhang-Hua Wang, Zhe Lai, Xiangjing School of Information Science and Engineering East China University of Science and Technology 130 Meilong Road Shanghai200237 China Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education Department of Computer Science LERIA Université d'Angers 2 Boulevard Lavoisier Angers49045 France Institut Universitaire de France 1 rue Descartes Paris75231 France Robotics Laboratory for Logistics Service Institute of Robotics and Intelligent Manufacturing Chinese University of Hong Kong Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518172 China Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210023 China

Population-based memetic algorithms have been successfully applied to solve many difficult combinatorial problems. Often, a population of fixed size was used in such algorithms to record some best solutions sampled during the search. However, given the particular features of the problem instance under consideration, a population of variable size would be more suitable to ensure the best search performance possible. In this work, we propose variable population memetic search (VPMS), where a strategic population sizing mechanism is used to dynamically adjust the population size during the memetic search process. Our VPMS approach starts its search from a small population of only two solutions to focus on exploitation, and then adapts the population size according to the search status to continuously influence the balancing between exploitation and exploration. We illustrate an application of the VPMS approach to solve the challenging critical node problem (CNP). We show that the VPMS algorithm integrating a variable population, an effective local optimization procedure (called diversified late acceptance search) and a backbone-based crossover operator performs very well compared to state-of-the-art CNP algorithms. The algorithm is able to discover new upper bounds for 13 instances out of the 42 popular benchmark instances, while matching 23 previous best-known upper bounds. Copyright © 2019, The Authors. All rights reserved.

关键词： Population statistics

Pothole Detection Based on Disparity Transformation and Road Surface Modeling

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Fan, Rui Ozgunalp, Umar Hosking, Brett Liu, Ming Pitas, Ioannis The Robotics Institute Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong Hong Kong The Electrical and Electronic Engineering Near East University Nicosia Cyprus The National Oceanography Centre Southampton United Kingdom The School of Informatics Aristotle University of Thessaloniki Thessaloniki Greece

Pothole detection is one of the most important tasks for road maintenance. computer vision approaches are generally based on either 2D road image analysis or 3D road surface modeling. However, these two categories are always used independently. Furthermore, the pothole detection accuracy is still far from satisfactory. Therefore, in this paper, we present a robust pothole detection algorithm that is both accurate and computationally efficient. A dense disparity map is first transformed to better distinguish between damaged and undamaged road areas. To achieve greater disparity transformation efficiency, golden section search and dynamic programming are utilized to estimate the transformation parameters. Otsu’s thresholding method is then used to extract potential undamaged road areas from the transformed disparity map. The disparities in the extracted areas are modeled by a quadratic surface using least squares fitting. To improve disparity map modeling robustness, the surface normal is also integrated into the surface modeling process. Furthermore, random sample consensus is utilized to reduce the effects caused by outliers. By comparing the difference between the actual and modeled disparity maps, the potholes can be detected accurately. Finally, the point clouds of the detected potholes are extracted from the reconstructed 3D road surface. The experimental results show that the successful detection accuracy of the proposed system is around 98.7% and the overall pixel-level accuracy is approximately 99.6%. Copyright © 2019, The Authors. All rights reserved.

关键词： Dynamic programming

Online multi-object tracking and segmentation with GMPHD filter and mask-based affinity fusion

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Song, Young-Min Yoon, Young-Chul Yoon, Kwangjin Jeon, Moongu Lee, Seong-Whan Pedrycz, Witold The School of Electrical Engineering and Computer Science Gwangju Institute of Technology Gwangju61005 Korea Republic of The Robotics Laboratory Hyundai Motor Company Gyeonggi-do 16082 Korea Republic of SI Analytics Co. Ltd. Daejeon34051 Korea Republic of The Department of Artificial Intelligence Korea University Seoul02841 Korea Republic of The Department of Brain and Cognitive Engineering Korea University Seoul02841 Korea Republic of The Department of Electrical and Computer Engineering University of Alberta EdmontonABT6R 2H5 Canada The Department of Electrical and Computer Engineering Faculty of Engineering King Abdulaziz University Jeddah21589 Saudi Arabia The Systems Research Institute Polish Academy of Sciences Warsaw01-447 Poland

In this paper, we propose a highly practical fully online multi-object tracking and segmentation (MOTS) method that uses instance segmentation results as an input. The proposed method is based on the Gaussian mixture probability hypothesis density (GMPHD) filter, a hierarchical data association (HDA), and a mask-based affinity fusion (MAF) model to achieve high-performance online tracking. The HDA consists of two associations: segment-to-track and track-to-track associations. One affinity, for position and motion, is computed by using the GMPHD filter, and the other affinity, for appearance is computed by using the responses from a single object tracker such as a kernalized correlation filter. These two affinities are simply fused by using a score-level fusion method such as min-max normalization referred to as MAF. In addition, to reduce the number of false positive segments, we adopt mask IoU-based merging (mask merging). The proposed MOTS framework with the key modules: HDA, MAF, and mask merging, is easily extensible to simultaneously track multiple types of objects with CPU-only execution in parallel processing. In addition, the developed framework only requires simple parameter tuning unlike many existing MOTS methods that need intensive hyperparameter optimization. In the experiments on the two popular MOTS datasets, the key modules show some improvements. For instance, ID-switch decreases by more than half compared to a baseline method in the training sets. In conclusion, our tracker achieves state-of-the-art MOTS performance in the test sets. Copyright © 2020, The Authors. All rights reserved.

关键词：

Robustness of DNA Strand Displacement Systems⋆⁎

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2018年第33期51卷 32-37页

作者： Nakakuki, Takashi Imura, Jun-ichi Kawamata, Ibuki Murata, Satoshi Department of Systems Design and Informatics School of Computer Science and Systems Engineering Kyushu Institute of Technology 680-4 Kawazu IizukaFukuoka820-8502 Japan Department of Mechanical and Environmental Informatics Tokyo Institute of Technology 2-12-1-W8-1 O-okayama Meguro-ku Tokyo152-8552 Japan Department of Robotics Graduate School of Engineering Tohoku University 6-6-1 Aoba Aramaki-Aza Aoba-Ward SendaiMiyagi980-8579 Japan

How to construct a reliable deoxyribonucleic acid (DNA) circuit is one of the most important issues in the field of molecular programming and computing. Such a circuit frequently suffers from various kinds of unintended binding reactions on account of a lower specificity of the molecular interaction emerging from base complementarity between DNA strands, which results in low reliability of the molecular circuit. In this study, we propose a method to quantitatively evaluate the robustness of a DNA circuit created by DNA strand displacement reactions. The highlight of our method is representing the circuit system contaminated by unintended reactions by a standard form of a disturbed nonlinear system and evaluating the robustness with the L2 gain by solving the Hamilton–Jacobi inequality. © 2018

关键词： Nucleic acids Differential equations DNA Electric network analysis Large scale systems Nonlinear equations Substitution reactions Binding reactions Circuit systems Dna strand displacements DNA strands Molecular circuits Molecular programming Nonlinear circuit Uncertainty

Single channel ecg for obstructive sleep apnea severity detection using a deep learning approach

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Banluesombatkul, Nannapas Rakthanmanon, Thanawin Wilaiprasitporn, Theerawit Bio-inspired Robotics and Neural Engineering Lab School of Information Science and Technology Vidyasirimedhi Institute of Science and Technology Thailand Department of Computer Engineering Kasetsart University Thailand

Obstructive sleep apnea (OSA) is a common sleep disorder caused by abnormal breathing. The severity of OSA can lead to many symptoms such as sudden cardiac death (SCD). Polysomnography (PSG) is a gold standard for OSA diagnosis. It records many signals from the patient's body for at least one whole night and calculates the Apnea-Hypopnea Index (AHI) which is the number of apnea or hypopnea incidences per hour. This value is then used to classify patients into OSA severity levels. However, it has many disadvantages and limitations. Consequently, we proposed a novel methodology of OSA severity classification using a Deep Learning approach. We focused on the classification between normal subjects (AHI 30). The 15-second raw ECG records with apnea or hypopnea events were used with a series of one-dimensional Convolutional Neural Networks (1-D CNN) for automatic feature extraction, deep recurrent neural networks with Long Short- Term Memory (LSTM) for temporal information extraction, and fuy-connected neural networks (DNN) for feature encoding from a large number of features until it closed to two classes. The main advantages of our proposed method include easier data acquisition, instantaneous OSA severity detection, and effective feature extraction without domain knowledge from expertise. To evaluate our proposed method, 545 subjects of which 364 were normal and 181 were severe OSA patients obtained from the MrOS sleep study (Visit 1) database were used with the kfold cross-validation technique. The accuracy of 79.45% for OSA severity classification with sensitivity, specificity, and F-score was achieved. This is significantly higher than the results from the SVM classifier with RR Intervals and ECG derived respiration (EDR) signal feature extraction. The promising result shows that this proposed method is a good start for the detection of OSA severity from a single channel ECG which can be obtained from wearable devices at home and can also be applied to near realtime

关键词： Feature extraction

A Novel Non-Cooperative Pose Measurement Method For Triangular Feature With Unknown Space Size 36

学校读者我要写书评

暂无评论

A Novel Non-Cooperative Pose Measurement Method For Triangul...

第36届中国控制会议

作者： Jun Yang Shunzhi Li Xueqian Wang Zhiheng Li Xuehai Gao Bin Liang National Laboratory for Information Science and Technology Tsinghua University Graduate School at Shenzhen Tsinghua University Shenzhen Laboratory of Space Robotics & Telescience Shenzhen Engineering Laboratory of Geometry Measurement Technology

ISBN: (纸本)9781538629185

In this paper,a novel method for measuring the relative pose of the triangular feature with unknown size is proposed by introducing line structured ***,the coordinate system model is established,and the relative relationship between each coordinate system is given;Secondly,by using the isosceles property of the triangular bracket and the line structured light constraint,three vertices' coordinates of the triangular feature and two intersection points between line structured light and the triangular feature are calculated in the camera coordinates;Then,the transfer matrix between the camera coordinate system and the world coordinate system is calculated by using the five feature points,and the transfer matrix is decomposed to obtain the relative position and attitude of the triangle feature plane;Finally,the mathematical simulation model is established and the measurement error factors are *** results show that the proposed method is effective and feasible.

关键词： Non-Cooperative Measurement Unknown Space Size Line Structured Light Triangular Feature

Towards asynchronous motor imagery-based brain-computer interfaces: A joint training scheme using deep learning

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Cheng, Patcharin Autthasan, Phairot Pijarana, Boriwat Chuangsuwanich, Ekapol Wilaiprasitporn, Theerawit Bio-inspired Robotics and Neural Engineering Lab School of Information Science and Technology Vidyasirimedhi Institute of Science & Technology Thailand Computer Engineering Department Chulalongkorn University Bangkok Thailand

In this paper, the deep learning (DL) approach is applied to a joint training scheme for asynchronous motor imagerybased Brain-computer Interface (BCI). The proposed DL approach is a cascade of one-dimensional convolutional neural networks and fully-connected neural networks (CNN-FC). The focus is mainly on three types of brain responses: non-imagery EEG (background EEG), (pure imagery) EEG, and EEG during the transitional period between background EEG and pure imagery (transitional imagery). The study of transitional imagery signals should provide greater insight into real-world scenarios. It may be inferred that pure imagery and transitional EEG are high and low power EEG imagery, respectively. Moreover, the results from the CNN-FC are compared to the conventional approach for motor imagery-BCI, namely the common spatial pattern (CSP) for feature extraction and support vector machine (SVM) for classification (CSP-SVM). Under a joint training scheme, pure and transitional imagery are treated as the same class, while background EEG is another class. Ten-fold crossvalidation is used to evaluate whether the joint training scheme significantly improves the performance task of classifying pure and transitional imagery signals from background EEG. Using sparse of just a few electrode channels (Cz, C3and C4), mean accuracy reaches 71.52% and 70.27% for CNN-FC and CSPSVM, respectively. On the other hand, mean accuracy without the joint training scheme achieve only 62.68% and 52.41% for CNN-FC and CSP-SVM, respectively. Copyright © 2018, The Authors. All rights reserved.

关键词： Brain computer interface