检索结果-内蒙古大学图书馆

SSRN 2022年

作者： Matsuura, Yuta Heming, Zhang Nakao, Kousuke Qiong, Chang Firmansyah, Iman Kawai, Shin Yamaguchi, Yoshiki Hayashi, Hisayoshi Maruyama, Tsutomu Nobuhara, Hajime The Department of Intelligent and Mechanical Interaction Systems Graduate School of Science and Technology University of Tsukuba 1-1-1 Tennoudai Ibaraki Tsukuba305-8573 Japan College of Engineering Systems School of Science and Engineering University of Tsukuba Japan The Department of Computer Science Graduate School of Science and Technology University of Tsukuba Japan The Faculty of Life and Environmental Sciences University of Tsukuba Japan The School of Computing Tokyo Institute of Technology Japan

We propose a high-precision plant height measurement system based on large-scale stereo images captured by a drone. In our system, the drone collects images of a field using a monocular camera and obtains the position data by a real time kinematic (RTK)-global navigation satellite system (GNSS). The heights of plants in the field are measured by stereo matching. By employing a single monocular camera rather than a binocular camera, we can obtain a sufficient baseline length for accurate height measurements, but the images must be precisely calibrated at run time. To this end, we propose a calibration algorithm with a conventional stereo matching algorithm. The proposed method requires only a pair of images and their position data (RTK-GNSS), which are more suitable for edge computing on drones than three-dimensional (3D) reconstructions by methods such as Structure from Motion. To show the effectiveness of the proposed method, we measured the plant height from photographs captured by the drone at different altitudes. Our method achieves a higher height resolution (1.6 cm) than the 3D reconstruction-based methods Pix4Dmapper and Metashape, with error-rate reductions of 62.2% and 69.4%, respectively, in the 10-20 m altitude range. When the altitude is lowered to 4.1 m , the depth resolution is improved to 1.6 mm with error reductions of 44.4% and 63.0% from those of Pix4Dmapper and Metashape, respectively. On a GTX 1080 TI graphics processing unit, stereo matching of 5472 × 3468-pixel images consumed 88 ms. This execution time is sufficiently fast for real-time measurements. Because our system uses the position data obtained by RTK-GNSS, it achieves centimeter-level accuracy during the drone flight. After the flight, the accuracy can be improved to millimeter level by comparing the results of the stereo matching with an image containing a reference plant of preobtained known height © 2022, The Authors. All rights reserved.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

A Novel & Innovative Blockchain-Empowered Federated Learning Approach for Secure Data Sharing in Smart City Applications 1

引用

International Conference on Advances in Communication Technology and computer Engineering, ICACTCE 2023

作者： Hai, Tao Wang, Dan Seetharaman, Tamizharasi Amelesh, M. Sreejith, P.M. Sharma, Vandana Ibeke, Ebuka Liu, Hong School of Computer and Information Qiannan Normal University for Nationalities Guizhou Duyun558000 China Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education Guizhou University Guizhou Guizhou550025 China School of Information and Artificial Intelligence Nanchang Institute of Science and Technology Nanchang China School of Mathematics and Statistics Qiannan Normal University for Nationalities Guizhou Duyun558000 China Key Laboratory of Complex Systems and Intelligent Optimization of Guizhou Province Guizhou Duyun558000 China Department of AI & ML Acharya Institute of Technology Bangalore India Amity Institute of Information Technology Amity University Noida Campus Noida India School of Creative and Cultural Business Robert Gordon University AberdeenAB10 7AQ United Kingdom

ISBN: (数字)9783031371646

ISBN: (纸本)9783031371639

The very existence of smart cities forms the stepping stone in the evolution of many technological advancements in the future era. While smart cities have already grown in their way, the tremendous amount of data generated from them paves the way for new perspectives of development. This is because security and privacy remain to be the major constraint across smart city applications. Further, smart city applications such as smart homes, smart transportation, and smart healthcare are generating a huge amount of data every day and it is often complex to collect and manage all the data together at a single location. To address these constraints, this paper presents a novel and innovative blockchain-assisted federated learning approach for secure data sharing in IoT Smart Cities. Here, we implement a federated learning approach, where the process of learning is made in a distributed fashion. The use of blockchain in turn adds more security and resilience to smart city applications. The security analysis proves that the proposed approach offers comparatively better performance and remains more resistant to various security threats and vulnerabilities. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Networks for Heterogeneous Unsupervised Domain Adaptation Detection

Generative Adversarial Networks for Heterogeneous Unsupervis...

引用

IEEE International Conference on intelligent Engineering systems (INES)

作者： Homayoun Safarpour Motealegh Mahalegi Amirfarhad Farhadi György Molnár Enikő Nagy Institute of Mechatronics and Vehicle Engineering Óbuda University Budapest Hungary Department of Computer Engineering Science and Research Branch Islamic Azad University Tehran Iran Kandó Kálmán Faculty of Electrical Engineering Óbuda University Budapest Hungary János Csere Apáczai Faculty Széchenyi University Győr Hungary Antal Bejczy Center for Intelligent Robotics John von Neumann Faculty of Informatics Óbuda University Budapest Hungary

ISBN: (数字)9798350367591

ISBN: (纸本)9798350367607

Domain adaptation, a subset of transfer learning, involves generating examples from two related but differently distributed source and target domains. This paper introduces an incremental adversarial learning method for unsupervised domain adaptation, where the source data is labeled, and the target data remains unlabeled. We employ a discriminative adversarial strategy as the primary technique for unsupervised domain adaptation to minimize the significant distributional variance between the source and target domains. Traditional domain adaptation methods typically train the source domain to align with a fixed target domain distribution. However, in many real-world scenarios, the target domain's distribution continuously evolves, leading to a lack of generalizability in the trained model for subsequent domains. To tackle this issue, we suggest using a continuous sequential domain adaptation method. This involves including instances from several related target domains in the training process in a sequential and continuous manner. This process ensures that all receiving domains are correctly aligned with their respective sources, and to maintain sequence continuity, the source domain is incrementally updated by incorporating the most reliable data from the current target domain. This enhancement aims to improve the network's training for forthcoming domain data. Leveraging the effectiveness of deep neural networks, our method utilizes deep GANs for domain adaptation. The approach enhances domain matching by augmenting the source with selected target data and introduces a novel strategy for continuous sequential domain matching. This involves a progressive update of source domain samples with reliable data from the current target domain, facilitating seamless adaptation to successive domain shifts. The proposed method demonstrated a high classification accuracy, achieving an impressive 99% and 95% in different settings. Furthermore, it outperforms previous studies rega

关键词： Training Adaptation models Machine learning algorithms Accuracy Transfer learning Clustering algorithms Sensitivity and specificity

来源：评论

学校读者我要写书评

暂无评论

Automatic Context-Driven Inference of Engagement in HMI: A Survey

arXiv

引用

arXiv 2022年

作者： Salam, Hanan Celiktutan, Oya Gunes, Hatice Chetouani, Mohamed SMART Lab New York University Abu Dhabi United Arab Emirates Department of Engineering King’s College LondonWC2R 2LS United Kingdom Department of Computer Science and Technology University of Cambridge CB3 0FD United Kingdom Institute of Intelligent Systems and Robotics CNRS UMR7222 Sorbonne University Paris France

An integral part of seamless human-human communication is engagement, the process by which two or more participants establish, maintain, and end their perceived connection. Therefore, to develop successful human-centered human-machine interaction applications, automatic engagement inference is one of the tasks required to achieve engaging interactions between humans and machines, and to make machines attuned to their users, hence enhancing user satisfaction and technology acceptance. Several factors contribute to engagement state inference, which include the interaction context and interactants’ behaviours and identity. Indeed, engagement is a multi-faceted and multi-modal construct that requires high accuracy in the analysis and interpretation of contextual, verbal and non-verbal cues. Thus, the development of an automated and intelligent system that accomplishes this task has been proven to be challenging so far. This paper presents a comprehensive survey on previous work in engagement inference for human-machine interaction, entailing interdisciplinary definition, engagement components and factors, publicly available datasets, ground truth assessment, and most commonly used features and methods, serving as a guide for the development of future human-machine interaction interfaces with reliable context-aware engagement inference capability. An in-depth review across embodied and disembodied interaction modes, and an emphasis on the interaction context of which engagement perception modules are integrated sets apart the presented survey from existing surveys. Copyright © 2022, The Authors. All rights reserved.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Bifurcations and Application of the Vallis – Model

Bifurcations and Application of the Vallis – Model

引用

International Conference on Computational Cybernetics (ICCC)

作者： Bálint Nagy György Molnár Antal Joós Enikő Nagy Department of Mathematics Institute of Computer Engineering University of Dunaújváros Dunaújváros Hungary Department of Applied Quantitative Methods Faculty of Finance and Accountancy Budapest Business University Budapest Hungary Department of Natural Sciences Kandó Kálmán Faculty of Electrical Engineering Institute of Electrophysics Óbuda University Budapest Hungary Kandó Kálmán Faculty of Electrical Engineering Óbuda University Budapest Hungary János Csere Apáczai Faculty Széchenyi University Győr Hungary John von Neumann Faculty Antal Bejczy Center for Intelligent Robotics institution">Institute of Cyberphysical Systems Óbuda University Budapest Hungary

ISBN: (数字)9798350350159

ISBN: (纸本)9798350350166

Investigating chaotic systems is a fertile field considering that chaos is an exotic chapter in the theory of differential equations, and it has useful applications in the theory of communications. In this work a well-known chaotic system is investigated from the bifurcation point of view and some applications are also introduced. The data studied are also visualized for better clarity. The results observed can be helpful in the encryption methods of the implementation of different communication channels.

关键词： Visualization Chaotic communication Communication systems Computational modeling Data visualization Computational cybernetics Differential equations

来源：评论

学校读者我要写书评

暂无评论

Multi-Seam Tracking with a Portable Robotic Welding System in Unstructured Environments

Research Square

引用

Research Square 2022年

作者： Yu, Shuangfei Guan, Yisheng Yang, Zhi Liu, Chutian Hu, Jiacheng Hong, Jie Zhu, Haifei Zhang, Tao School of Electro-mechanical Engineering Guangdong University of Technology Guangzhou510006 China Department of Physical Intelligence Max-Planck Institute for Intelligent Systems Stuttgart70569 Germany School of Engineering and Computer Science Australian National University CanberraACT2601 Australia

Most welding manufacturing of the heavy industry, such as shipbuilding and construction, is carried out in an unstructured workspace. The term Unstructured indicates the production environment is irregular, changeable and without model. In this case, the changeable workpiece position, workpiece shape, environmental background, and environmental illumination should be carefully considered. Because of such complicated characteristics, the welding is currently being relied on the manual operation, resulting in high cost, low efficiency and quality. This work proposes a portable robotic welding system and a novel seam tracking method. Compared to existing methods, it can cope with more complex general spatial curve weld. Firstly, the tracking pose of the robot is modeled by a proposed dual-sequence tracking strategy. On this basis, the working parameters can be adjusted to avoid robot-workpiece collision around the workpiece corners during the tracking process. By associating the forward direction of the welding torch with the viewpoint direction of the camera, it solves the problem that the weld feature points are prone to be lost in the tracking process by conventional methods. Point cloud registration is adopted to globally locate the multi-segment welds in the workpiece, since the system deployment location is not fixed. Various experiments on single or multiple welds under different environmental conditions show that even if the robot is deployed in different positions, it can reach the starting point of the weld smoothly and accurately track along the welds. © 2022, CC BY.

关键词： Welds

来源：评论

学校读者我要写书评

暂无评论

KDCTime: Knowledge distillation with calibration on inceptiontime for time-series classification

arXiv

引用

arXiv 2021年

作者： Gong, Xueyuan Si, Yain-Whar Tian, Yongqi Lin, Cong Zhang, Xinyuan Liu, Xiaoxiang School of Intelligent Systems Science and Engineering Jinan University Zhuhai China Department of Computer and Information Science University of Macau China School of Optoelectronics Beijing Institute of Technology Beijing China

Time-series classification approaches based on deep neural networks are easy to be overfitting on UCR datasets, which is caused by the few-shot problem of those datasets. Therefore, in order to alleviate the overfitting phenomenon for further improving the accuracy, we first propose Label Smoothing for InceptionTime (LSTime), which adopts the information of soft labels compared to just hard labels. Next, instead of manually adjusting soft labels by LSTime, Knowledge Distillation for InceptionTime (KDTime) is proposed in order to automatically generate soft labels by the teacher model. At last, in order to rectify the incorrect predicted soft labels from the teacher model, Knowledge Distillation with Calibration for InceptionTime (KDCTime) is proposed, where it contains two optional calibrating strategies, i.e. KDC by Translating (KDCT) and KDC by Reordering (KDCR). The experimental results show that the accuracy of KDCTime is promising, while its inference time is two orders of magnitude faster than ROCKET with an acceptable training time overhead. © 2021, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Driving-Torque Self-Adjusted Triboelectric Nanogenerator for Effective Harvesting of Random Wind Energy

SSRN

引用

SSRN 2022年

作者： Wang, Yuqi Li, Xiang Yu, Xin Zhu, Jianyang Shen, Ping Wang, Zhong Lin Cheng, Tinghai Beijing Institute of Nanoenergy and Nanosystems Chinese Academy of Sciences Beijing101400 China Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Wuhan430081 China State Key Laboratory of Internet of Things for Smart City Department of Civil and Environmental Engineering University of Macau Macao999078 China School of Materials Science and Engineering Georgia Institute of Technology AtlantaGA30332-0245 United States

Triboelectric nanogenerators (TENGs), as a new energy technology for distributed power, are used widely in the field of the natural environment energy harvesting. Because the natural energy is random and unstable, dynamic matching between TENGs driving-torque and natural environment energy is fundamental for improving the applications of TENGs. Therefore, a driving-torque self-adjusted triboelectric nanogenerator (SA-TENG) for effective harvesting of random wind energy is developed in this paper. When the external wind speed is unstable, the SA-TENG automatically self-adjusted its driving-torque to dynamically match the wind speed and obtain higher output power. Experiments showed that the SA-TENG can adjust its driving-torque in accordance to the wind speed ranging in 5.0–13.2 m/s, and that, the output peak power can reach 7.69 mW. Under the same conditions, in comparison with a normal TENG, the power growth rate and the highest energy conversion efficiency of the SA-TENG were boosted by more than 4.3 and 12.2 times, respectively;values that are also 3.2 and 6.5 times higher, respectively, than those of an electromagnetic generator. Additionally, the SA-TENG can supply power to sensors for monitoring environment, proving its feasibility as a distributed energy source. © 2022, The Authors. All rights reserved.

关键词： Nanogenerators

来源：评论

学校读者我要写书评

暂无评论

Infrared Invisible Clothing: Hiding from Infrared Detectors at Multiple Angles in Real World

arXiv

引用

arXiv 2022年

作者： Zhu, Xiaopei Hu, Zhanhao Huang, Siyuan Li, Jianmin Hu, Xiaolin School of Integrated Circuits Tsinghua University Beijing China Department of Computer Science and Technology Institute for Artificial Intelligence State Key Laboratory of Intelligent Technology and Systems BNRist Tsinghua University Beijing China IDG/McGovern Institute for Brain Research Tsinghua University Beijing China Beijing China

Thermal infrared imaging is widely used in body temperature measurement, security monitoring, and so on, but its safety research attracted attention only in recent years. We proposed the infrared adversarial clothing, which could fool infrared pedestrian detectors at different angles. We simulated the process from cloth to clothing in the digital world and then designed the adversarial "QR code" pattern. The core of our method is to design a basic pattern that can be expanded periodically, and make the pattern after random cropping and deformation still have an adversarial effect, then we can process the flat cloth with an adversarial pattern into any 3D clothes. The results showed that the optimized "QR code" pattern lowered the Average Precision (AP) of YOLOv3 by 87.7%, while the random "QR code" pattern and blank pattern lowered the AP of YOLOv3 by 57.9% and 30.1%, respectively, in the digital world. We then manufactured an adversarial shirt with a new material: aerogel. Physical-world experiments showed that the adversarial "QR code" pattern clothing lowered the AP of YOLOv3 by 64.6%, while the random "QR code" pattern clothing and fully heat-insulated clothing lowered the AP of YOLOv3 by 28.3% and 22.8%, respectively. We used the model ensemble technique to improve the attack transferability to unseen models. Copyright © 2022, The Authors. All rights reserved.

关键词： Thermography (imaging)

来源：评论

学校读者我要写书评

暂无评论

Impedance control for a novel composite modular lower-limb hemiplegic exoskeleton

Impedance control for a novel composite modular lower-limb h...

引用

2021 IEEE International Conference on Real-Time Computing and robotics, RCAR 2021

作者： Bao, Ruoyu Li, Pengbo He, Bailin Wang, Can Wu, Xinyu Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen518055 China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology University of Chinese Academy of Sciences Department of Mechanical and Automation Engineering Chinese University of Hong Kong College of Mechanical and Electrical Engineering Shaanxi University of Science and Technology Shaanxi Xi'an710021 China

ISBN: (纸本)9781665436786

This paper proposes a control scheme based on impedance control for the smoothing control of the operating movements of a lower-limb hemiplegic exoskeleton robot on the basis of a new composite modular lower-limb hemiplegic ex-oskeleton(CMLHE) structure. The CMLHE has good structural performance and can be used in the rehabilitation of patients with hemiplegia caused by stroke and other diseases. At the same time, the smoothing control by means of impedance control ensures that patients with lower limb hemiplegia can use the CMLHE to achieve smooth walking movements without additional injuries caused by the CMLHE during the rehabilitation training. This paper analyses the performance of this CMLHE robot based on walking movements and demonstrates through kinematic and kinetic modelling and simulation that the impedance control scheme of this CMLHE robot is feasible and effective and can be more widely used in the rehabilitation training of patients with lower limb hemiplegia. © 2021 IEEE.

关键词： Exoskeleton (robotics)

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：