检索结果-内蒙古大学图书馆

IEEE International conference on Robotics and Automation (ICRA)

作者： Zhang, Zhiyuan Ma, Huan Zhou, Yulin Ji, Jingjing Yang, Hua Huazhong Univ Sci & Technol Sch Mech Sci & Engn State Key Lab Intelligent Mfg Equipment & Technol Wuhan Peoples R China

ISBN: (纸本)9798350384581;9798350384574

Accurate perception of the surrounding environment stands as a primary objective for robots. Through tactile interaction, vision-based tactile sensors provide the capability to capture high-resolution and multi-modal surface information of objects, thereby facilitating robots in achieving more dexterous manipulations. However, the prevailing GelSight sensors entail intricate calibration procedures, posing challenges in their application on curved surfaces and requiring the maintenance of stable lighting conditions throughout experimentation. Additionally, constrained by shape and structure, current vision-based tactile sensors are predominantly applied to measurements within a limited area. In this study, we design a novel cylindrical vision-based tactile sensor that enables continuous and swift perception of large-scale object surfaces through rolling. To tackle the challenges posed by laborious calibration processes, we propose a self-supervised photometric stereo method based on deep learning, which eliminates precalibration requirements and enables the derivation of surface normals from a single image without relying on stable lighting conditions. Finally, we perform surface reconstruction from normal and point cloud registration on the multiple frames of images obtained by rolling the cylindrical sensor, resulting in large surface reconstruction. We compare our method with the representative lookup table method in the GelSight sensors. The results show that the proposed method enhances both reconstruction accuracy and robustness, thereby demonstrating the potential of the proposed sensor in large-scale surface reconstruction. Codes and mechanical structures are available at: https://***/ZhangZhiyuanZhang/GelRoller

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Tensor Completion Using High-Order Spatial Delay Embedding for IoT Multi-Attribute Data Reconstruction

引用

IEEE TRANSACTIONS ON SIGNAL AND information processing OVER networks 2024年 10卷 715-728页

作者： Zhang, Xiaoyue He, Jingfei Liu, Xiaotong North China Univ Sci & Technol Sch Artificial Intelligence Hebei Key Lab Ind Intelligent Percept Qinhuangdao 063210 Hebei Peoples R China Hebei Univ Technol Sch Elect & Informat Engn Tianjin Key Lab Elect Mat & Devices Tianjin 300401 Peoples R China

Restricted by various factors, the data collected by sensor nodes in some Internet of Things (IoT) can only provide spatio-temporal low-resolution multi-attribute information of the monitored area. Estimating environmental data in sensorless deployment locations to achieve spatio-temporal high-resolution multi-attribute data sensing has become an urgent problem. Existing IoT data reconstruction methods either suffer from performance degradation due to continuous data loss or ignore the correlation among multi-attribute data. To overcome these two shortcomings, a multi-attribute data reconstruction method utilizing a high-order spatial delay-embedding transform is proposed in this work. Strict low-rank property can be achieved in the proposed method without additional constraints, avoiding overcomplicating the model by combining too many constraints. The tensor ring decomposition is used to approximate the rank of the formulated data and to efficiently solve the tensor completion model via the alternating least squares algorithm. Experimental results on IoT data demonstrate that the proposed method outperforms the state-of-the-art low-rank-based methods on multi-attribute data reconstruction.

关键词： Tensors Interpolation Correlation sensors Data models Spatiotemporal phenomena Matrix decomposition Multi-attribute data reconstruction low-rank tensor completion Internet of Things spatiotemporal correlation

来源：评论

学校读者我要写书评

暂无评论

Research Progress in Multi-sensor Data Fusion Algorithms 24

Research Progress in Multi-Sensor Data Fusion Algorithms

引用

2024 7th International conference on Computer information Science and Artificial Intelligence, CISAI 2024

作者： Jiang, Huhai Ke, Huimeng Southwest Institute of Technical Physics Sichuan Chengdu China

ISBN: (纸本)9798400707254

With the rapid advancement of modern science and technology, the importance of multi-sensor data fusion technology in various applications has become increasingly prominent. However, traditional non-intelligent fusion methods reveal many shortcomings when dealing with complex and dynamic environments. These methods rely on preset models and algorithms, showing poor adaptability to system nonlinearities, time-varying characteristics, and uncertainties, making it challenging to achieve real-time, efficient, and accurate information fusion. Moreover, traditional methods often struggle with processing multi-source heterogeneous data, being easily affected by noise and interference, thus reducing fusion accuracy and system robustness. intelligent multi-sensor data fusion algorithms, by incorporating advanced technologies such as machine learning, deep learning, neural networks, and reinforcement learning, can dynamically learn and adapt to environmental changes, automatically adjusting fusion strategies and overcoming the limitations of traditional methods. This paper presents a multi-sensor data fusion algorithm based on an improved BP neural network, enhanced by particle swarm optimization (PSO) to improve network performance. This method prevents premature convergence of the network, speeds up convergence, and thus enhances data fusion accuracy. The study of intelligent multi-sensor information fusion algorithms holds significant practical significance and broad application prospects. By systematically summarizing and analyzing recent research progress in intelligent fusion algorithms, this paper reveals the unique advantages of intelligent fusion technologies in improving fusion accuracy, enhancing system robustness, and adaptability. It also explores their potential applications in various fields and identifies future development directions and research priorities. © 2024 Copyright held by the owner/author(s).

关键词： information fusion

来源：评论

学校读者我要写书评

暂无评论

CLOUD-ENHANCED WIRELESS sensor networks FOR AIR QUALITY MONITORING

CLOUD-ENHANCED WIRELESS SENSOR NETWORKS FOR AIR QUALITY MONI...

引用

2024 International conference on Sustainable Computing and Integrated Communication in Changing Landscape of AI, ICSCAI 2024

作者： Shreenidhi, H.S. Agrawal, Trapty Kale, Kiran Karnataka Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Department of Electronics and Communication Engineering Presidency University Karnataka Bangalore India

ISBN: (纸本)9798350355338

A growing trend in environmental monitoring involves the use of inexpensive wireless sensors to create densely dispersed networks that provide higher spatial resolution than traditional air quality control systems. In this study, a novel air quality monitoring system-a wireless sensors network, or WSN, made up of a dispersed sensor network connected to a cloud system-is presented. The sensor nodes use low-power ZigBee motes to send field measurements in real time to the cloud via a dedicated gateway. An optimally calibrated cloud computing framework has been instituted to effectively retain, oversee, handle, and present the data originating from the sensor system. Optimised chemical and contaminant identification is made possible by using artificial intelligence tools in the cloud for sophisticated data handling and analysis. This system is unique in that it is small, light, and energy-efficient, allowing for the deployment of several nodes for thorough air quality evaluations in various locations. The effectiveness of the method in identifying common volatile organic chemicals including the compounds benzene, toluene, ethane, and xylene to is validated by a practical example in a laboratory environment. Principal component analysis, perceptron networks with backpropagation learning, and help vector computation methods are all used in the data processing. The results show that the volatile organic compound concentrations may be distinguished and quantified with good accuracy. Cloud computing, air quality, chemical sensors, and wireless sensor networks are among the key themes. © 2024 IEEE.

关键词： Zigbee

来源：评论

学校读者我要写书评

暂无评论

Lab Scale Demonstration of Pipeline Third- Party Damage Classification Using Convolutional Neural networks. 33

Lab Scale Demonstration of Pipeline Third- Party Damage Clas...

引用

conference on Signal processing, sensor/information Fusion, and Target Recognition XXXIII

作者： Bukka, Sandeep Lalam, Nageswara Bhatta, Hari Wright, Ruishu Natl Energy Technol Lab 626 Cochran Mill Rd Pittsburgh PA 15236 USA NETL Res Support Contractor 626 Cochran Mill Rd Pittsburgh PA 15236 USA Oak Ridge Inst Sci & Educ ORISE 1299 Bethel Valley Rd Oak Ridge TN 37830 USA

ISBN: (纸本)9781510674332;9781510674325

Gas pipelines are critical for transporting vast quantities of natural gas across regions. Third-party damage, such as unauthorized excavation activities is a primary cause of accidents and damage to these pipelines, leading to significant economic losses, environmental harm, and potential threats to human safety. The importance of detecting third-party damages as early as possible cannot be overstated, as it allows pipeline operators to take timely actions to prevent damage. Recent technological advancements, particularly the development of fiber optic sensors, offer promising solutions for real-time monitoring and early warning systems against such damages. Analyzing incidents related to third-party damages present significant challenges due to their non-adherence to physical laws, in contrast to phenomena like corrosion, temperature, and pressure changes. Traditional analytical or empirical models fall short of detecting such damages effectively. However, deep learning techniques have demonstrated notable success in identifying distinctive features from non-physical data sources, including images, speech, and third-party damage acoustic signals pertinent to this study. The efficacy of deep learning methods is contingent upon the availability of a robust dataset for training. The scarcity of fiber optic sensor data pertaining to third-party damages is a critical limitation in this field. This research aims to mitigate this challenge by generating a dataset of third-party damage events on a laboratory scale utilizing a single mode-multi mode-single mode (SMS) fiber acoustic sensor. The sound samples representative of various third-party activities, such as vehicle movements, excavation, and digging were sourced from open-source databases. These samples were then played through a speaker in proximity to an SMS sensor, and the resultant fiber acoustic vibration data were recorded for each event. This process yielded a collection of 200 samples across 13 distinct thir

关键词： Acoustics sensors Data modeling Deep learning Fiber optics sensors Convolution Convolutional neural networks Machine learning Safety

来源：评论

学校读者我要写书评

暂无评论

An Optimized Edge Platform for 3D Object Detection in Autonomous Driving

An Optimized Edge Platform for 3D Object Detection in Autono...

引用

2025 International conference on Electronics, information, and Communication, ICEIC 2025

作者： Bok, Kwonseung Kim, Yumi Kim, Aeri Lee, Sang-Seol Kim, Kyungho Intelligent Image Processing Research Center Korea Electronics Technology Institute Gyeonggi-do Korea Republic of

ISBN: (纸本)9798331510756

Autonomous driving technology has been developed to enhance the safety of vehicles and drivers by recognizing surrounding objects and making appropriate situational judgments using sophisticated sensors. In particular, 3D object detection networks utilizing LiDAR within deep learning models have advanced to achieve accurate object detection. However, performing 3D object detection using LiDAR and advanced sensors requires processing a massive amount of data, making it challenging to handle directly within the vehicle. While external computational resources such as cloud servers can be employed, this approach introduces difficulties in guaranteeing low data exchange latency and ensuring data stability and security. In this paper, we propose a method to process 3D object detection on an edge platform, enabling it to be handled locally for autonomous driving applications. The proposed edge platform consists of a hardware architecture optimized for processing large volumes of point cloud data and a quantized, lightweight network. This enables the edge platform to handle the entire process of acquiring point cloud data via LiDAR, performing 3D object detection, and executing image post-processing tasks directly on the device. © 2025 IEEE.

关键词： 3D-object detection Autonomous driving Edge platform

来源：评论

学校读者我要写书评

暂无评论

GAFormer: Wearable IMU-Based Human Activity Recognition with Gramian Angular Field and Transformer

GAFormer: Wearable IMU-Based Human Activity Recognition with...

引用

Asia-Pacific-Signal-and-information-processing-Association Annual Summit and conference (APSIPA ASC)

作者： Trung-Hieu Le Thai-Khanh Nguyen Trung-Kien Tran Thanh-Hai Tran Cuong Pham Hanoi Univ Sci & Technol Sch Elect & Elect Engn Hanoi Vietnam Dainam Univ Hanoi Vietnam Mil Informat Technol Inst Hanoi Vietnam Posts & Telecom Inst Technol Dept Comp Sci Hanoi Vietnam

ISBN: (纸本)9798350300673

Recognizing human activities (HAR) from wearable motion sensors has widely practical applications due to its low cost, convenient use, and scalability. Plenty of works utilize 1D CNN or RNN to capture temporal information from time series, while others take advantage of 2D CNN architectures that can effectively handle spatial correlation, and distinctive recognition features, which are really useful for recognition tasks. This paper proposes GAFormer, a method, which exploits the latter, for human activity recognition from wearable motion sensors. GAFormer transforms the raw IMU data into a Gramian Angular Difference Field (GADF) image, which encodes the pair-wise angles between different sensor readings to capture the temporal dynamics and relationships among the sensor measurements. Next, a transformer model is employed to extract visual features from GADF images effectively. In addition, we adapted a state-of-the-art transformer CoAtNet as the backbone of GAFormer. GAFormer is evaluated over two published datasets C-MHAD and GesHome. With the accuracies of 98% on C-MHAD and 95.5% on GesHome's subset, GAFormer demonstrates that combining the GADF technique and a transformer model could be feasible and promising for motion sensor-based action recognition.

关键词： Human activity recognition inertial sensors features extraction Convolutional Neural networks Transformers Gramian Angular Field

来源：评论

学校读者我要写书评

暂无评论

Enhancing Energy and Coverage Efficiency of Underground Wireless sensor Network Using Relay Node in Smart Agriculture 10th

Enhancing Energy and Coverage Efficiency of Underground Wi...

引用

10th EAI International conference on Industrial networks and intelligent Systems, INISCOM 2024

作者： Mai, Ha Thi Tran, Tuan Toan Le, Minh Tuan Nguyen, Tran Quoc Vinh Nguyen, Thi Huong Quynh Le, Hoang Son Faculty of Information Technology University of Science and Education - University of Danang Da Nang Viet Nam Faculty of Information Technology Thanglong University Hanoi Viet Nam National Academy of Public Administration Hanoi Viet Nam Artificial Intelligence Research Centre VNU Information Technology Institute Vietnam National University Hanoi Viet Nam Department of Science Technology and Environment Ministry of Education and Training Ha Noi Viet Nam

ISBN: (纸本)9783031673566

Smart agriculture is one of the many domains in which recent developments in radio and sensor technologies enable environmental monitoring. The sensors are responsible for collecting data from various subterranean and terrestrial settings, which are subsequently transmitted to the central base station. This data is then utilized to make informed decisions on environmental control measures aimed at optimizing crop growth. Despite the fact that they offer more intelligent services, they have difficulties in terms of concerns such as energy consumption and coverage. This research proposes building wireless sensor networks in smart agriculture with relay nodes to maximize energy and coverage for subterranean and above-ground sensors. The paper introduces a clustering model that incorporates ideas for selecting the most suitable number of relay nodes in a network. The findings indicate that by reducing the number of disconnected nodes in the network by a factor of 2.1, while requiring just 1/5 of the relay nodes, the wireless sensor network may achieve improved energy efficiency and expanded coverage area. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Method for Complexing information from intelligent sensors of Mobile Components of Monitoring Systems 13th

Method for Complexing Information from Intelligent Sensors o...

引用

13th Computer Science Online conference

作者： Melnik, E. V. Orda-Zhigulina, M. V. Safronenkova, I. B. Kapustyan, S. G. Rodina, A. A. Puha, I. S. Russian Acad Sci Southern Sci Ctr St Chehova 41 Rostov Na Donu 344006 Russia

ISBN: (纸本)9783031705946;9783031705953

It is proposed in the work a method for integrating information from smart sensors of mobile components of monitoring systems based on distributed ledger technologies, "fog" and "cloud" computing. The method combines a developed method for recording user data into a distributed key-value database at the level of a distributed functional application DApp and a modified method for dynamically changing consensus and a modified method for validation of block's in open distributed decentralized systems with unreliable information. The developed method provides high write speed and increases the reliability of storing user data by dynamically changing the volume of transactions when writing useful data to the registry and dynamically taking into account the network configuration features when writing data to the registry. The use of the proposed method of integrating information from smart sensors makes it possible to reduce the speed of writing user data to the registry by reducing the degree of "openness" of the registry, which is suitable for heterogeneous monitoring systems where participants have different access rights.

关键词： Monitoring data collection systems processing distributed ledger mobile components consensus algorithm verification algorithm data storage

来源：评论

学校读者我要写书评

暂无评论

Research on Computer Aided Ship intelligent Cruise System 2

Research on Computer Aided Ship Intelligent Cruise System

引用

2nd International conference on Mechatronics, IoT and Industrial Informatics, ICMIII 2024

作者： Yang, Baicheng Dalian Maritime University Navigation College Dalian China

ISBN: (数字)9798350386639

ISBN: (纸本)9798350386639

In this paper, the intelligent microcontroller as the core of the ship intelligent navigation research. Combined with MCU, it realizes digital-to-analog conversion, state control, and active fault analysis and detection. The control device consists of a GPS receiving assembly, a computer, a cabin signal processor, a main engine fuel sensor, a main engine speed sensor and related interface devices. Two sensors transmit the monitored speed, fuel level and other two pieces of information to the cabin signal processor through the RS485 interface. The measurement results are processed by the engine control unit and transmitted to the main engine. The GPS receiver transmits the measured ship operation to the host through the RS485 interface. This paper realizes high-speed acquisition and processing of ship intelligent navigation by optimizing navigation algorithm. At the same time, the design also has the ability of navigation positioning, which can effectively ensure the smooth operation of the ship's electrical equipment to ensure the safety of navigation. © 2024 IEEE.

关键词： Digital to analog conversion

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：