检索结果-内蒙古大学图书馆

3rd IEEE International conference on Automation and Computation, AUTOCOM 2025

作者： Krishnakumar, S. Acharjya, Kalyan Khurana, Shivam Swain, Rakesh Ranjan Rampal, Sourav Manjunath, C. Sathyabama Institute of Science and Technology Department of Biomedical Engineering Tamil Nadu Chennai India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Centre of Research Impact and Outcome Chitkara University Punjab Rajpura140417 India Odisha Bhubaneswar India Chitkara Centre for Research and Development Chitkara University Himachal Pradesh Baddi174103 India Karnataka Bangalore India

ISBN: (纸本)9798331542375

sensor fusion integrates data from multiple sensors to provide a more accurate, reliable, and contextual sense of the surrounding environment. So, it became a key method for correct monitoring in battery-dependent Internet of Things clever environments, especially Indoor tracking. There is only one dedicated sensor. To benefit the most from it and surround these weaknesses in complex indoor environments with wrongness. The sensor fusion methods for accurate indoor tracking in IoT-based Smart Environments are proposed to solve the problems above by integrating data from multiple sources, including Wi-Fi APs and BLE beacons, RFID readers, and IMUs. This results in a more complete and detailed view of the environment crucial for location-based applications such as asset tracking, localization, or navigation within smart buildings. There are many algorithms to fuse sensor data. The algorithms process the sensor data and give a fused result that outperforms all of these individual components. sensor fusion in IoT-based smart environments improves indoor tracking accuracy, robustness, and scalability. It also permits real-time tracking localization of objects and people;it is the key to optimally managing smart environments. The sensor fusion method generally improves indoor tracking properties in the rapidly growing IoT-based smart environments. © 2025 IEEE.

关键词： Accurate applications Environment Integrates Properties

来源：评论

学校读者我要写书评

暂无评论

SIUNet: Sparsity Invariant U-Net for Edge-Aware Depth Completion 23

SIUNet: Sparsity Invariant U-Net for Edge-Aware Depth Comple...

引用

23rd IEEE/CVF Winter conference on applications of Computer Vision (WACV)

作者： Ramesh, Avinash Nittur Giovanneschi, Fabio Gonzalez-Huici, Maria A. Fraunhofer FHR Wachtberg Germany

ISBN: (纸本)9781665493468

Depth completion is the task of generating dense depth images from sparse depth measurements, e.g., LiDARs. Existing unguided approaches fail to recover dense depth images with sharp object boundaries due to depth bleeding, especially from extremely sparse measurements. State-ofthe-art guided approaches require additional processing for spatial and temporal alignment of multi-modal inputs, and sophisticated architectures for data fusion, making them non-trivial for customized sensor setup. To address these limitations, we propose an unguided approach based on UNet that is invariant to sparsity of inputs. Boundary consistency in reconstruction is explicitly enforced through auxiliary learning on a synthetic dataset with dense depth and depth contour images as targets, followed by fine-tuning on a real-world dataset. With our network architecture and simple implementation approach, we achieve competitive results among unguided approaches on KITTI benchmark and show that the reconstructed image has sharp boundaries and is robust even towards extremely sparse LiDAR measurements.

关键词： Training Laser radar Image edge detection Computer architecture Network architecture sensor systems Task analysis

来源：评论

学校读者我要写书评

暂无评论

Research on the fusion of Autonomous Navigation algorithms and Environmental Perception in Intelligent Ship Technology 5

Research on the Fusion of Autonomous Navigation Algorithms a...

引用

5th IEEE International conference on Power, Electronics and Computer applications, ICPECA 2025

作者： Zhang, Zhijie Zong, Yonggang Binzhou Polytechnic Ocean Department Binzhou China

ISBN: (纸本)9798331533694

The research focus of this paper is on the organic combination of autonomous navigation algorithm and environmental perception technology, with the aim of enhancing the autonomous navigation capability of intelligent ships in complex marine environments. Autonomous navigation relies on the close coordination of multiple perception systems and algorithms, among which the simultaneous localization and mapping (SLAM) algorithm is particularly critical. The SLAM algorithm generates high-precision environmental maps in real time and provides accurate ship positioning by fusing multi-sensor information. This paper proposes and designs an autonomous navigation system that integrates environmental perception and SLAM technology. Its system architecture includes sensor data processing, path planning and control decision modules. The effectiveness of the proposed algorithm is verified through a series of model simulations, and experimental evaluation is carried out in multiple test scenarios. The simulation results show that compared with traditional navigation methods, the algorithm significantly improves the navigation accuracy and safety of ships in complex marine environments, and the positioning error rate is reduced by more than 15%. The research results of this paper provide a solid theoretical basis and technical support for the future research and development of autonomous navigation systems for intelligent ships. © 2025 IEEE.

关键词： Marine navigation

来源：评论

学校读者我要写书评

暂无评论

Timeseries-aware Uncertainty Wrappers for Uncertainty Quantification of Information-fusion-Enhanced AI Models based on Machine Learning 53

Timeseries-aware Uncertainty Wrappers for Uncertainty Quanti...

引用

53rd Annual IEEE/IFIP International conference on Dependable Systems and Networks (DSN)

作者： Gross, Janek Klaes, Michael Joeckel, Lisa Gerber, Pascal Fraunhofer IESE Data Sci Kaiserslautern Germany

ISBN: (纸本)9798350325430

As the use of Artificial Intelligence (AI) components in cyber-physical systems is becoming more common, the need for reliable system architectures arises. While data-driven models excel at perception tasks, model outcomes are usually not dependable enough for safety-critical applications. In this work, we present a timeseries-aware uncertainty wrapper for dependable uncertainty estimates on timeseries data. The uncertainty wrapper is applied in combination with information fusion over successive model predictions in time. The application of the uncertainty wrapper is demonstrated with a traffic sign recognition use case. We show that it is possible to increase model accuracy through information fusion and additionally increase the quality of uncertainty estimates through timeseries-aware input quality features.

关键词： uncertainty estimation traffic sign recognition data fusion sensor fusion image classification dependability autonomous driving perception uncertainty runtime verification

来源：评论

学校读者我要写书评

暂无评论

Research on the Standard System and Key Technologies of Digital Substation Technology

Research on the Standard System and Key Technologies of Digi...

引用

2024 International conference on Innovative Design and Intelligent Manufacturing, IDIM 2024

作者： Yang, Weihong Huang, Zhiming Zhang, Li Chen, Qiulin Qian, Hai CSG Electric Power Research Institute Co. Ltd. CSG Guangdong 510663 China Electrical Science Institute of Guizhou Power Grid Co. Ltd. CSG Guiyang550000 China China Southern Power Grid Co. Ltd. CSG Guangdong 510663 China

ISBN: (纸本)9781643685427

This paper proposes a digital substation standard system to enhance management efficiency. It introduces a model for comprehensive digital information perception and Bayesian algorithms for monitoring. Wireless sensor identification collects subsystem data, analyzed by decision tree clustering. Key meta-data scheduling and fusion methods integrate digital information across the substation. Digital twin technology enables dynamic data fusion and sharing, optimizing substation management. © 2024 The Authors.

关键词： sensor data fusion

来源：评论

学校读者我要写书评

暂无评论

Non-Invasive Human-Machine Interface (HMI) Systems With Hybrid On-Body sensors for Controlling Upper-Limb Prosthesis: A Review

引用

IEEE sensorS JOURNAL 2022年第11期22卷 10292-10307页

作者： Zhou, Hao Alici, Gursel Univ Wollongong ARC Ctr Excellence Electromat Sci Sch Mech Mat Mechatron & Biomed Engn Wollongong NSW 2522 Australia

In this work, we present a systematic review on non-invasive HMIs employing hybrid wearable sensor modalities for recognition of upper limb intentions. Different combinations of the sensors are investigated. As sEMG is dominant in the applications of externally powered prosthetic hands, it is involved in most hybrid sensor combinations. The combined use of sEMG and IMU is most studied in the literature as IMU is easy to be integrated. Though limited, the investigation on other hybrid modalities has been drawing more and more research attention and efforts, especially those with FMG and NIRS. For all the reported hybrid sensors, it is verified that this strategy can enrich the information of user intention and help the pattern recognition and/or intensity regulation of robotic hand/arm prosthesis. Though it is the trend, the development of these hybrid-sensor-based HMIs are still at the preliminary stage. More dedicated sensor fusion models and system architectures as well as new hybrid features and algorithms need to be developed to make the best use of each sensing modality's strength to achieve robust and stable user intention recognition, which is essential for the progress and user acceptance of upper limb prosthesis.

关键词： sensors Muscles Robot sensing systems Robustness Electroencephalography Biosensors sensor systems Human-machine-interface HMI upper limb prosthesis hybrid modalities multi-modal sensor fusion sEMG plus MMG sEMG plus FMG sEMG plus SMG sEMG plus NIRS robustness adaptive learning

来源：评论

学校读者我要写书评

暂无评论

Trust-Based Data fusion and Machine Learning for Underwater sensor Networks 4

Trust-Based Data Fusion and Machine Learning for Underwater ...

引用

4th IEEE Asian conference on Innovation in Technology, ASIANCON 2024

作者： Kanavalli, Anita Chaudhari, Shilpa Shashikant Bharathi, S. Ramaiah Institute of Technology Department of Cse Bangalore India

ISBN: (纸本)9798350354218

Underwater Wireless sensor Networks (UWSNs) are essential for a wide range of marine applications, from environmental monitoring to underwater exploration. However, significant obstacles such signal attenuation, multipath propagation, and sensor node mobility make it difficult to sustain flawless communication in dynamic underwater environments. In UWSNs, handover prediction becomes essential for maintaining continuous communication and maximizing the effectiveness of data transfer. This research presents a novel method for precise handover prediction in UWSNs by utilizing machine learning algorithms and real-time maritime data. The system attempts to predict Energy Trust, Environment Trust, and Communication Trust events by examining environmental parameters and past handover events, improving communication efficiency and reliability in dynamic underwater environments. © 2024 IEEE.

关键词： sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Combining Knowledge Distillation and Transfer Learning for sensor fusion in Visible and Thermal Camera-based Person Classification 18

Combining Knowledge Distillation and Transfer Learning for S...

引用

18th International conference on Machine Vision and applications (MVA)

作者： John, Vijay Kawanishi, Yasutomo RIKEN Guardian Robot Project Tokyo Japan

ISBN: (纸本)9784885523434

Visible and thermal camera-based sensor fusion has shown to address the limitations and enhance the robustness of visible camera-based person classification. In this paper, we propose to further enhance the classification accuracy of visible-thermal person classification using transfer learning, knowledge distillation, and the vision transformer. In our work, the visible-thermal person classifier is implemented using the vision transformer. The proposed classifier is trained using the transfer learning and knowledge distillation techniques. To train the proposed classifier, visible and thermal teacher models are implemented using the vision transformers. The multimodal classifier learns from the two teachers using a novel loss function which incorporates the knowledge distillation. The proposed method is validated on the public Speaking Faces dataset. A comparative analysis with baseline algorithms and an ablation study is performed. The results show that the proposed framework reports an enhanced classification accuracy.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

ROS Powered Autonomous Mobile Robot for Indoor applications

ROS Powered Autonomous Mobile Robot for Indoor Applications

引用

2024 International conference on Intelligent algorithms for Computational Intelligence Systems, IACIS 2024

作者： Madan, H.T. Mahesh, L. Sajjad, Mohammed Nitte India Reva University School of Electronics and Communication Engineering Bangalore India

ISBN: (纸本)9798350360660

In the realm of indoor robotics, navigation poses a critical challenge across service robots, humanoids, and warehouse automation. Existing techniques like line following, RFID tracking, and Aruco marker-based systems exhibit limitations in autonomy and adaptability. This has created a need for the development of an advanced and sophisticated autonomous navigation system that encompasses self-reliant perception, planning, and control capabilities. The proposed system makes use of LiDAR technology for mapping and Robot operating system for planning and control which takes place on Jetson Nano GPU platform, providing real-time processing power for environmental data. LiDAR sensors offer accurate environmental perception, obstacle detection, and adaptability to dynamic indoor settings. The system employs BLDC wheels and an aluminium base for versatility, supporting loads up to 120 kg. Additionally, it incorporates an IMU sensor with EKF sensor fusion for accurately estimating the robot's position. This flexible design has applications in various indoor robotics scenarios, ranging from complex service tasks to efficient warehouse operations. This versatile design finds applications in various indoor robotics scenarios, from complex service tasks to efficient warehouse operations. © 2024 IEEE.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

An efficient hardware implementation of LED lightweight block cipher 7

An efficient hardware implementation of LED lightweight bloc...

引用

IEEE 7th International conference on Advanced Technologies, Signal and Image Processing (ATSIP)

作者： Mhaouch, Ayoub Ayadi, Wadhah Ridha, Sarra Issa, Khaled Ben Abdelali, Abdessalem Machhout, Mohsen Univ Monastir Fac Sci Monastir Lab Elect & Microelect EuE Monastir Tunisia Univ Monastir Higher Inst Comp Sci & Math Monastir ISIMMM Monastir Tunisia

ISBN: (纸本)9798350351491;9798350351484

New technologies like the Internet of Things (IoT), Radio Frequency Identification (RFID), and Wireless sensor Networks pose unique challenges due to their limited power and real-time demands. Among these challenges, ensuring efficient and low-latency encryption systems is paramount. To address these challenges, lightweight encryption algorithms like LED cipher have emerged in recent years. LED offers a promising balance between efficiency and security, making it ideal for securing IoT devices. In the present work, we present two distinct hardware architectures for the LED block cipher tailored for devices with limited resources, employing a 32-bit data path. These architectures aim to optimize performance and resource utilization while maintaining robust security. The iterative architecture offers parallel processing for faster encryption/decryption but requires higher hardware resources, while the serial architecture sequentially performs operations to minimize resource consumption. Experimental results demonstrate the efficacy of the suggested hardware architectures, highlighting low latency and high throughput compared to existing hardware implementations of various block ciphers. Our findings indicate that both architectures provide efficient solutions for implementing the LED algorithm in resource-constrained environments.

关键词： LED block cipher IoT applications hardware architecture resource optimization serial architecture high-performance FPGA

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：