检索结果-内蒙古大学图书馆

4th International Conference on Information science, Parallel and Distributed Systems, ISPDS 2023

作者： Jiang, Chengjia Wang, Tao Li, Sien Wang, Jinyang Wang, Shirui Antoniou, Antonios Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou China Fujian Education Institutions Wuyi University The Key Laboratory of Cognitive Computing and Intelligent Information Processing Wuyishan China College of Computer and Data Science Fuzhou University Fuzhou China European University Cyprus Department of Computer Science and Engineering Nicosia Cyprus

ISBN: (纸本)9798350337181

We address the problem of learning new classes for semantic segmentation models from few examples, which is challenging because of the following two reasons. Firstly, it is difficult to learn from limited novel data to capture the underlying class distribution. Secondly, it is challenging to retain knowledge for existing classes and to avoid catastrophic forgetting. For learning from limited data, we propose a pseudo-labeling strategy to augment the few-shot training annotations in order to learn novel classes more effectively. Given only one or a few images labeled with the novel classes and a much larger set of unlabeled images, we transfer the knowledge from labeled images to unlabeled images with a coarse-to-fine pseudo-labeling approach in two steps. Specifically, we first match each labeled image to its nearest neighbors in the unlabeled image set at the scene level, in order to obtain images with a similar scene layout. This is followed by obtaining pseudo-labels within this neighborhood by applying classifiers learned on the few-shot annotations. In addition, we use knowledge distillation on both labeled and unlabeled data to retain knowledge on existing classes. We integrate the above steps into a single convolutional neural network with a unified learning objective. Extensive experiments on the Cityscapes and KITTI datasets validate the efficacy of the proposed approach in the self-driving domain. Code is available from https://***/ChasonJiang/FSCILSS. © 2023 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Whole Body Balance Control for Bipedal Robots Based on Virtual Model Control 16th

Whole Body Balance Control for Bipedal Robots Based on Virtu...

引用

16th International Conference on intelligent robotics and Applications, ICIRA 2023

作者： Gao, Chengzhi Xie, Ye Zhu, Yiting Liang, Dingkun Kong, Lingyu Wang, Xin Xie, Anhuan Gu, Jianjun Research Center for Intelligent Robotics Research Institute of Interdisciplinary Innovation Zhejiang Laboratory Hangzhou311100 China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou311100 China Zhejiang University Zhejiang Hangzhou311100 China Department of Electrical and Computer Engineering Dalhousie University HalifaxNSB3H 4R2 Canada

ISBN: (纸本)9789819964918

Due to the lack of accurate stability theoretical basis, the dynamic balance control of bipedal robots is a challenging topic. In this paper, we propose a controller that combines virtual model control and whole body control. In our framework, the whole system is simplified into a spring inverted pendulum model. Decoupling control is carried out for this model, and a virtual model is introduced to establish the relationship between the joint torque of the support leg and the state of the center of mass. The distribution of reaction force is obtained through decoupling closed-loop control. The whole body control part first uses multi task whole body control to determine the kinematics information, and then solves the joint feedforward torque through dynamical model, thus obtaining the desired force position hybrid control. Proposed algorithm improved the problem of incomplete decoupling between states and increased the stiffness of the support leg. The newly designed control framework was tested in Simscape dynamic simulation and verified the anti-interference ability and fast walking ability of Whole Body Balance Control for bipedal robots based on Virtual Model Control. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Inverted pendulum

来源：评论

学校读者我要写书评

暂无评论

Face detection technology based on skin color features in MATLAB 3

Face detection technology based on skin color features in MA...

引用

3rd International Conference on Machine Vision, Automatic Identification, and Detection, MVAID 2024

作者： Dang, Longfei Yang, Miao Jing, Xiaodong Xu, Yizhi Xiao, Qicheng He, Wanyu Intelligent Policing Key Laboratory of Sichuan Province Sichuan Police College LuZhou China Department of Computer Science and Technology Sichuan Police College LuZhou China Department of Crimina Technology Sichuan Police College LuZhou China

ISBN: (纸本)9781510681880

Face detection is the most basic processing in the face recognition process. If the detection method is not appropriate, it can cause the recognition process to collapse. Face detection is very important in face recognition. The facial pattern is very complex and susceptible to external interference. Common facial detection algorithms generally have weaknesses such as high computational complexity, slow speed, and high false alarm rates. In this paper, a skin color model detection method based on the YCbCr color space is used for facial detection, which solves the problem of high computational complexity. Morphological theory is also used for subsequent image processing. © 2024 SPIE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Attention-Based Hybrid Deep Learning Model for Intrusion Detection in IIoT Networks 28th

Attention-Based Hybrid Deep Learning Model for Intrusion Det...

引用

28th International Conference on Knowledge Based and intelligent information and Engineering Systems, KES 2024

作者： Ullah, Safi Boulila, Wadii Koubaa, Anis Ahmad, Jawad Robotics and Internet-of-Things Laboratory Prince Sultan University Riyadh12435 Saudi Arabia Department of Computer Science Quaid-i-Azam University Islamabad44000 Pakistan RIADI Laboratory National School of Computer Science University of Manouba Manouba Tunisia School of Computing Edinburgh Napier University EdinburghEH10 5DT United Kingdom

The integration of Industrial Internet of Things (IIoT) technology into the industrial sector has produced numerous significant advantages. However, the notable concern remains the absence of robust security and privacy measures in these interconnected critical environments. To secure IIoT networks, several researchers and experts employ intrusion detection systems (IDS) for detecting cyberattacks. The current systems exhibit efficient performance when handling a few categories of attack classes, even in the presence of slight imbalances. However, these models face challenges when confronted with vast categories of attack classes and highly imbalanced data. To tackle these issues, this study introduces an attention-based hybrid deep learning (AB-HDL) model designed to monitor network traffic and predict cyberattacks within the network. The proposed model comprises an attention mechanism and a hybrid deep learning model that integrates convolutional neural networks (CNN) and an autoencoder (AE). The effectiveness of the proposed AB-HDL is assessed using publicly accessible datasets: Edge-IIoTset and X-IIoTID. To ascertain the efficacy of AB-HDL, a comparative analysis is conducted with various other machine learning (ML) and deep learning (DL) algorithms. The outcome analysis indicates that the proposed AB-HDL surpasses the performance of the other algorithms and exhibits optimal efficiency in detecting cyber attacks within IIoT networks. © 2024 The Authors.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

PointPillars Backbone Type Selection for Fast and Accurate LiDAR Object Detection

PointPillars Backbone Type Selection for Fast and Accurate L...

引用

International Conference on computer Vision and Graphics, ICCVG 2022

作者： Lis, Konrad Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Al. Mickiewicza 30 Krakow30-059 Poland

ISBN: (纸本)9783031220241

3D object detection from LiDAR sensor data is an important topic in the context of autonomous cars and drones. In this paper, we present the results of experiments on the impact of backbone selection of a deep convolutional neural network on detection accuracy and computation speed. We chose the PointPillars network, which is characterised by a simple architecture, high speed, and modularity that allows for easy expansion. During the experiments, we paid particular attention to the change in detection efficiency (measured by the mAP metric) and the total number of multiply-addition operations needed to process one point cloud. We tested 10 different convolutional neural network architectures that are widely used in image-based detection problems. For a backbone like MobilenetV1, we obtained an almost 4x speedup at the cost of a 1.13% decrease in mAP. On the other hand, for CSPDarknet we got an acceleration of more than 1.5x at an increase in mAP of 0.33%. We have thus demonstrated that it is possible to significantly speed up a 3D object detector in LiDAR point clouds with a small decrease in detection efficiency. This result can be used when PointPillars or similar algorithms are implemented in embedded systems, including SoC FPGAs. The code is available at https://***/vision-agh/pointpillars-backbone. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Advances in self-powered sports monitoring sensors based on triboelectric nanogenerators

引用

Journal of Energy Chemistry 2023年第4期79卷 477-488页

作者： Fengxin Sun Yongsheng Zhu Changjun Jia Tianming Zhao Liang Chu Yupeng Mao Physical Education Department Northeastern UniversityShenyang 110819LiaoningChina Institute of Carbon Neutrality and New Energy&School of Electronics and Information Hangzhou Dianzi UniversityHangzhou 310018ZhejiangChina School of Strength and Conditioning Training Beijing Sport UniversityBeijing 100084China State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of ScienceShenyang 110016LiaoningChina Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang 110016LiaoningChina

The new era of the internet of things brings great opportunities to the field of intelligent *** collection and analysis of sports data are becoming more intelligent driven by the widely-distributed sensing network *** nanogenerators(TENGs)can collect and convert energy as selfpowered sensors,overcoming the limitations of external power supply,frequent power replacement and high-cost ***,we introduce the working modes and principles of TENGs,and then summarize the recent advances in self-powered sports monitoring sensors driven by TENGs in sports equipment facilities,wearable equipment and competitive sports *** discuss the existing issues,i.e.,device stability,material sustainability,device design rationality,textile TENG cleanability,sports sensors safety,kinds and manufacturing of sports sensors,and data collection comprehensiveness,and finally,propose the *** work has practical significance to the current TENG applications in sports monitoring,and TENG-based sensing technology will have a broad prospect in the field of intelligent sports in the future.

关键词： Triboelectric nanogenerator Wearable energy sensors Sport monitoring

来源：评论

学校读者我要写书评

暂无评论

A Multi-stage Single-Point Incremental Sheet Forming for Enhanced Homogeneous Thickness Distribution

A Multi-stage Single-Point Incremental Sheet Forming for Enh...

引用

International Conference on Control, Decision and Information Technologies (CoDIT)

作者： Ghadeer Issa Karam Almaghout Alexander Maloletov Alexandr Klimchik Intelligent Robotics Systems Laboratory Institute of Robotics and Computer Vision Innopolis University Innopolis Russia Lincoln Centre for Autonomous Systems (L-CAS) School of Computer Science University of Lincoln Lincoln United Kingdom

ISBN: (数字)9798350373974

ISBN: (纸本)9798350373981

This paper introduces a multi-stage approach to enhance homogeneous thickness distribution in single-point incremental sheet forming. Traditional methods often struggle with achieving uniform material thickness, compromising the final part’s structural integrity and performance. Our proposed methodology leverages a V-shape starting stage, systematically designed to address these challenges by improving material flow and distribution throughout the forming process. We employ finite element analysis to validate the efficiency of the proposed approach and compare it with conventional single-stage forming processes. The simulations demonstrate significant improvements in achieving a more uniform thickness distribution across the formed parts. The comparative analysis highlights the potential of the proposed multi-stage approach for industrial applications and enhances material homogeneity. This methodology advances the precision and reliability of formed parts and opens new avenues for research and development in sheet metal forming technologies.

关键词： Geometry Accuracy Shape Simulation Metals Production Manufacturing Reliability Information technology Research and development

来源：评论

学校读者我要写书评

暂无评论

Security and Privacy Concerns for Healthcare Wearable Devices and Emerging Alternative Approaches 10th

Security and Privacy Concerns for Healthcare Wearable Devi...

引用

10th EAI International Conference on Wireless Mobile Communication and Healthcare, MobiHealth 2021

作者： Boumpa, Eleni Tsoukas, Vasileios Gkogkidis, Anargyros Spathoulas, Georgios Kakarountas, Athanasios Intelligent Systems Laboratory Department of Computer Science and Biomedical Informatics University of Thessaly Lamia Greece Gjovik Norway

ISBN: (纸本)9783031063671

The wide use of wearable devices rises a lot of concerns about the privacy and security of personal data that are collected and stored by such services. This concern is even higher when such data is produced by healthcare monitoring wearable devices and thus the impact of any data leakage is more significant. In this work a classification of the wearable devices used for healthcare monitoring is conducted, and the most prominent relevant privacy and security issues and concerns are presented. Furthermore, a brief review of alternative approaches that can eliminate most of such issues, including federated learning, homomorphic encryption, and tinyML, is presented. The aim of this work is to present the privacy and security concerns in healthcare monitoring wearable devices, as well as some solutions in hot topics about these issues. © 2022, ICST Institute for computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

A study on an applied behavior analysis-based robot-mediated listening comprehension intervention for ASD

引用

Paladyn 2021年第1期12卷 31-46页

作者： Geoffrey Louie, Wing-Yue Korneder, Jessica Abbas, Ibrahim Pawluk, Cristyn Intelligent Robotics Laboratory Department of Electrical and Computer Engineering Oakland University RochesterMI48307 United States Applied Behavior Analysis Clinic Department of Human Development and Child Studies Oakland University RochesterMI48307 United States Intelligent Robotics Laboratory Department of Electrical and Computer Engineering Oakland University RochesterMI48307 United States

Autism spectrum disorder (ASD) is a lifelong developmental condition that affects an individual’s ability to communicate and relate to others. Despite such challenges, early intervention during childhood development has shown to have positive long-term benefits for individuals with ASD. Namely, early childhood development of communicative speech skills has shown to improve future literacy and academic achievement. However, the delivery of such interventions is often time-consuming. Socially assistive robots (SARs) are a potential strategic technology that could help support intervention delivery for children with ASD and increase the number of individuals that healthcare professionals can positively affect. For SARs to be effectively integrated in real-world treatment for individuals with ASD, they should follow current evidence-based practices used by therapists such as Applied Behavior Analysis (ABA). In this work, we present a study that investigates the efficacy of applying well-known ABA techniques to a robot-mediated listening comprehension intervention delivered to children with ASD at a university-based ABA clinic. The interventions were delivered in place of human therapists to teach study participants a new skill as a part of their overall treatment plan. All the children participating in the intervention improved in the skill being taught by the robot and enjoyed interacting with the robot, as evident by high occurrences of positive affect as well as engagement during the sessions. One of the three participants has also reached mastery of the skill via the robot-mediated interventions. © 2021 Wing-Yue Geoffrey Louie et al., published by De Gruyter.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Correction to: Improving time and energy efficiency in multi-UAV coverage operations by optimizing the UAVs’ initial positions (International Journal of intelligent robotics and Applications, (2024), 10.1007/s41315-024-00333-2)

引用

International Journal of intelligent robotics and Applications 2024年第1期9卷 365-373页

作者： Stefanopoulou, Aliki Raptis, Emmanuel K. Apostolidis, Savvas D. Gkelios, Socratis Kapoutsis, Athanasios Ch. Chatzichristofis, Savvas A. Vrochidis, Stefanos Kosmatopoulos, Elias B. Information Technologies Institute The Centre for Research & ampTechnology Hellas 6th km Harilaou - Thermis Thessaloniki57001 Greece Department of Electrical and Computer Engineering Democritus University of Thrace Kimmeria Campus Xanthi67100 Greece Intelligent Systems Laboratory Department of Computer Science Neapolis University Pafos 2 Danais Avenue PafosCY 8042 Cyprus

In the original publication, the author has found few errors in the figures 2, 4, 11 and 12 which significantly impact both the paper's quality and the reputation of the journal. These issues undermine the clarity of the methodology and the novelty of the research. 1. Each column represents a different case in the experiment, corresponding to the number of UAVs in both the obstacle-free and obstacle areas. However, in Fig. 2, the first row contains identical subfigures across all columns, while the subfigures in the remaining rows are identical to each other The incorrect Fig. 2 appears as below: (Figure presented.) However the corrected Fig. 2 should appear as below. (Figure presented.) 2. In Fig. 4, every row showcase the average QoF for the testing scenarios (obstacle-free and obstacle area). However the first row has the exact same figures with the second row. The incorrect Fig. 4 appears as below: (Figure presented.) However the corrected Fig. 4 should appear as below. (Figure presented.) 3. Figures 11 and 12 showcase the distribution of each Quality of Flight (QoF) metric value for every UAV in the conducted trials during the testing scenarios. However, Fig. 11 is the same with Fig. 12. The incorrect Figs. 11 and 12 appears as below: (Figure presented.) However the corrected Figs. 11 and 12 should appear as below. (Figure presented.) Distribution of each Quality of Flight metric value for every UAV in the conducted trials during the coverageof the obstacle-free area Distribution of each Quality of Flight metric value for every UAV in the conducted trials during the coverageof the obstacle area The original article has been corrected. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

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：