检索结果-内蒙古大学图书馆

Proceedings of the 2025 3rd International conference on Communication networks and Machine Learning

作者： Qi Li Luhao Zhao Haifeng Wang Shuang Gao Shanpeng Wei Min Lu School of Computer and Communication Engineering Nanjing Tech University Pujiang Institute Nanjing Jiangsu China

ISBN: (纸本)9798400713231

In order to improve the efficiency and accuracy of marine water quality monitoring, an intelligent monitoring system based on multi-parameter buoys was designed. Through the comprehensive design of software and hardware systems, the intelligent level of marine environmental monitoring is improved. The study covers real-time monitoring and data collection of key parameters such as surface salinity, chlorophyll concentration, wind speed, wind direction, temperature, profile flow rate, etc. The system framework consists of a hardware part (multi-parameter sensor and buoy design) and a software part (data acquisition and processing platform). At the same time, correlation and normalization algorithms are introduced for data processing and analysis to mine valuable information from marine water quality data. The experimental results show that the error of the system in the monitoring of salinity, chlorophyll concentration, temperature and other parameters is less than 5%, and the relative error of profile flow velocity monitoring is 3.2%, and the overall accuracy meets the needs of marine environmental monitoring. Finally, this study aims to provide an effective solution for marine water quality monitoring and promote the sustainable development of the marine environment.

关键词： Data processing

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient PPG-Based Respiratory Rate Estimation Using Spiking Neural networks

引用

sensors 2024年第12期24卷 3980页

作者： Yang, Geunbo Kang, Youngshin Charlton, Peter H. Kyriacou, Panayiotis A. Kim, Ko Keun Li, Ling Park, Cheolsoo Kwangwoon Univ Dept Comp Engn Seoul 01897 South Korea Univ Cambridge Dept Publ Hlth & Primary Care Cambridge CB1 8RN England City Univ London Sch Sci & Technol SST Dept Engn London EC1V 0HB England LG Elect AI Lab Seoul 06763 South Korea

Respiratory rate (RR) is a vital indicator for assessing the bodily functions and health status of patients. RR is a prominent parameter in the field of biomedical signal processing and is strongly associated with other vital signs such as blood pressure, heart rate, and heart rate variability. Various physiological signals, such as photoplethysmogram (PPG) signals, are used to extract respiratory information. RR is also estimated by detecting peak patterns and cycles in the signals through signal processing and deep-learning approaches. In this study, we propose an end-to-end RR estimation approach based on a third-generation artificial neural network model-spiking neural network. The proposed model employs PPG segments as inputs, and directly converts them into sequential spike events. This design aims to reduce information loss during the conversion of the input data into spike events. In addition, we use feedback-based integrate-and-fire neurons as the activation functions, which effectively transmit temporal information. The network is evaluated using the BIDMC respiratory dataset with three different window sizes (16, 32, and 64 s). The proposed model achieves mean absolute errors of 1.37 +/- 0.04, 1.23 +/- 0.03, and 1.15 +/- 0.07 for the 16, 32, and 64 s window sizes, respectively. Furthermore, it demonstrates superior energy efficiency compared with other deep learning models. This study demonstrates the potential of the spiking neural networks for RR monitoring, offering a novel approach for RR estimation from the PPG signal.

关键词： spiking neural network physiological signal healthcare photoplethysmogram respiratory rate

来源：评论

学校读者我要写书评

暂无评论

Text Guided Road Marking Point Cloud Completion

Text Guided Road Marking Point Cloud Completion

引用

Next Generation Data-driven networks (NGDN), International conference on

作者： Xu He Qihong Xu Huan Luo College of Computer and Data Science Fuzhou University Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China

ISBN: (数字)9798350388374

ISBN: (纸本)9798350388381

With the continuous development of intelligent transportation technologies such as autonomous driving and navigation, accurate perception of road markings becomes crucial. However, due to limitations in sensor perspectives and obstacles blocking the view, the scanned point cloud of road markings is often incomplete, potentially leading to erroneous decisions in intelligent transportation systems. Therefore, it becomes imperative to recover complete road markings from these incomplete point clouds. This paper proposes a text-guided road marking completion method, which integrates text information with point cloud data using attention mechanisms. By leveraging text information to guide the network in completing road marking point clouds, the proposed method aims to enhance the perception accuracy and completeness of road markings. Experimental validation on road marking datasets demonstrates the effectiveness and feasibility of the proposed approach.

关键词： Point cloud compression Accuracy Attention mechanisms Navigation Fuses Roads Transportation Diffusion models Robustness Next generation networking

来源：评论

学校读者我要写书评

暂无评论

Low Complexity Heuristics for Multi-Objective sensor Placement in Traffic networks

Low Complexity Heuristics for Multi-Objective Sensor Placeme...

引用

International conference on intelligent Transportation

作者： Marina Sofokleous Yiolanda Englezou Aristotelis Savva Stelios Timotheou Christos G. Panayiotou Department of Electrical and Computer Engineering KIOS Research and Innovation Center of Excellence University of Cyprus Public Works Department of the Ministry of Transport Communications & Works Nicosia Cyprus

Monitoring the traffic state of the road network is very important for a plethora of reasons, such as the prevention of traffic congestion and the development of estimation and control policies. In order to efficiently obtain high-quality information on traffic, the sensors must be installed at optimal locations in the road network under study. This problem is known as the Network sensor Location Problem (NSLP). In this work, a multi-objective NSLP is proposed for the installation of a pre-defined number of sensors to maximise (i) the covered traffic flow volume and (ii) the minimum distance between candidate links for sensor installation, while taking into account pre-installed sensors. We reformulate the problem into a single-objective mixed-integer linear program (MILP) that yields the optimal sensor locations. In addition, we propose four low-complexity heuristics for the solution of the problem. The performance of the proposed algorithms is evaluated for the traffic network of the Republic of Cyprus under real-life conditions and traffic data. Results show that the four low-complexity approaches yield a different trade-off between execution speed and solution quality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Design for Backscatter-Assisted Wireless Powered IRS-NOMA networks

Energy Efficient Design for Backscatter-Assisted Wireless Po...

引用

IEEE conference on Wireless Communications and Networking

作者： Reza Jafari Abraham O. Fapojuwo Department of Electrical and Computer Engineering University of Calgary Canada

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

This paper explores the use of an intelligent reflecting surface (IRS) in backscatter-assisted wireless powered non-orthogonal multiple access (NOMA) networks. In these networks, energy-constrained sensors first harvest energy from a power station with the help of an IRS in the downlink (DL) phase. They then transmit information to an access point using NOMA during the uplink (UL) phase. When sensors have low energy levels, they can switch from the high-power conventional mode to the low-power backscatter mode. By utilizing a practical energy harvesting model that captures realistic rectifier characteristics, we propose a new algorithm that optimizes DL energy harvesting time, UL backscatter time, UL conventional data transmission time, and DL phase-shift vector. Additionally, we analyze the impact of imperfect channel estimation on system performance. The numerical results demonstrate that IRS provides at least 30 % energy efficiency improvements.

关键词： Wireless communication NOMA Wireless sensor networks Energy efficiency Vectors Delays Data communication

来源：评论

学校读者我要写书评

暂无评论

Embracing Data Irregularities in Multivariate Time Series with Recurrent and Graph Neural networks 12th

Embracing Data Irregularities in Multivariate Time Series w...

引用

12th Brazilian conference on intelligent Systems, BRACIS 2023

作者： de Barros, Marcel Rodrigues Rissi, Thiago Lizier Cabrera, Eduardo Faria Tannuri, Eduardo Aoun Gomi, Edson Satoshi Barreira, Rodrigo Augusto Costa, Anna Helena Reali Universidade de São Paulo SP São Paulo Brazil Petróleo Brasileiro S.A. Rio de Janeiro Brazil

ISBN: (纸本)9783031453670

Data collection in many engineering fields involves multivariate time series gathered from a sensor network. These sensors often display differing sampling rates, missing data, and various irregularities. To manage these issues, complex preprocessing mechanisms are required, which become coupled with any statistical model trained with the transformed data. Modeling the motion of seabed-anchored floating platforms from measurements is a typical example for that. We propose and analyze a model that uses both recurrent and graph neural networks to handle irregularly sampled multivariate time series, while maintaining low computational cost. In this model, each time series is represented as a node in a heterogeneous graph, where edges depict the relationships between each measured variable. The time series are encoded using independent recurrent neural networks. A graph neural network then propagates information across the time series using attention layers. The outcome is a set of updated hidden representations used by the recurrent neural networks to create forecasts in an autoregressive manner. This model can generate forecasts for all input time series simultaneously while remaining lightweight. We argue that this architecture opens up new possibilities as the model can be integrated into low-capacity systems without needing expensive GPU clusters for inference. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Grinded Surface Roughness Prediction Using Data-Driven Models with Contact Force information

Grinded Surface Roughness Prediction Using Data-Driven Model...

引用

IEEE/ASME International conference on Advanced intelligent Mechatronics (AIM)

作者： Lai, Jing-Yu Lin, Pei-Chun Natl Taiwan Univ NTU Dept Mech Engn 1 Roosevelt Rd Sec 4 Taipei 106 Taiwan

ISBN: (数字)9781665413084

ISBN: (纸本)9781665413084

Surface roughness plays an important role in grinding;it can represent the grinding quality of machined parts. In previous research, analytical models and empirical models have been used to predict surface roughness. This research presented surface roughness prediction models based on linear regression and artificial neural networks of several types of model structures, then applied different features as model inputs, including force data directly get from the force sensor and those collected force data after statistical processing to reduce dimension. After conducting the prediction model, a self-developed grinding machine was used to collect the force data for model training and testing, and the mean absolute percentage error was used to evaluate the prediction performance. In the end, a neural network of three hidden layers was marked as the best model, which was useful for surface roughness prediction during grinding.

关键词： Grinding surface roughness prediction linear regression neural network contact force

来源：评论

学校读者我要写书评

暂无评论

State Management Against Two-message Attacks in Hash-Based Post Quantum Signatures for Large IoT sensor networks Using Blockchain 6

State Management Against Two-message Attacks in Hash-Based P...

引用

6th International conference on Applied Computational Intelligence in information Systems, ACIIS 2023

作者： Kok Seng, Vincent Lew Thien Wan, Au Shah Newaz, S.H. Universiti Teknologi Brunei School of Computing and Informatics Bandar Seri Begawan Brunei

ISBN: (纸本)9798350317428

With the rise of quantum computers, quantum-safe digital signatures have been invented to ensure the security and verifiability of communication. Hash-based one-time signatures are one of the candidates to ensure unforgeability against the improved processing power. This signature algorithm requires tracking of secret keys to ensure one-time usage, called key state. In an Internet of Things(IoT) environment, failure to maintain key state due to network failures, hardware/software failures, implementation flaws, and improper access is possible. Consequences of failure to manage key state results in the degradation of the system's security, opening up opportunities for attackers to forge signatures. Solutions to this however are limited due to the scale and resource constraints of IoT devices. Hence, this paper proposes a solution named, Blockchain-based Key State Management to ensure the key state is maintained without affecting resources and scalability heavily. The solution utilizes blockchain and smart contracts to maintain key states by leveraging blockchain protocols to ensure key states remain updated and un-tampered. The paper also contains a qualitative survey comparing other alternative solutions for preventing key reuse to highlight the importance of the proposed solution. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Wearable Photonic-based Artificial Throat for Speech Detection and Recognition

Wearable Photonic-based Artificial Throat for Speech Detecti...

引用

Signal, information and Data processing (ICSIDP), IEEE International conference on

作者： Wenbo Li Di Zheng Kun Xiao Zhuo Wang Lanfang Liu Rui Min The Center for Information Photonics & Communications School of Information Science and Technology Southwest Jiaotong University Chengdu China Department of Physics Faculty of Arts and Sciences Beijing Normal University Zhuhai China Department of Psychology Faculty of Arts and Sciences Beijing Normal University Zhuhai China Center for Cognition and Neuroergonomics State Key Laboratory of Cognitive Neuroscience and Learning Beijing Normal University Zhuhai China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

A wearable photonic-based artificial throat was proposed through the integration of optical fiber sensing and AI technologies. An optical fiber sensor, composed of polymer optical fibers (POFs) and elastomer optical fiber, serves as the core of the intelligent artificial throat. The optical fiber sensor is encapsulated within Dragon Skin 20 films, whose elastic modulus closely mimics that of human tissue, as a photonic-based artificial throat. This artificial throat exhibits a rapid response time, enabling it to detect minute vibrations such as airflow and muscle vibrations, which can then be converted into controlled sound. Finally, an AI algorithm was integrated with the proposed artificial throat, enabling the recognition of three monosyllabic words ("good," "age," and "book") with 100% accuracy. This successful combination of optical fiber sensing technology with AI demonstrates its applicability to the emerging field of voice control.

关键词： Vibrations Optical fiber sensors Accuracy Films Speech recognition Skin sensors Time factors Artificial intelligence Photonics

来源：评论

学校读者我要写书评

暂无评论

An Embedded System based Curtain Controlling Unit using NRF Module

An Embedded System based Curtain Controlling Unit using NRF ...

引用

Image processing and Capsule networks (ICIPCN), International conference on

作者： Akshay Sidral Vaishnav Thakare Rohini Sontakke Dinesh Gaikwad Prachi Rajarapollu School of Electrical Engineering MIT Academy of Engineering Alandi Pune India

ISBN: (数字)9798350367171

ISBN: (纸本)9798350367188

With the growing interconnectedness and intelligent automation, the 21st century is seeing a fast change in technology, industries, and practices. The concept of “interconnectivity” first appeared in the context of intelligent control systems, which promoted interactions and communication between technology, sensors, and people. Numerous real-world applications for these systems exist in the industrial sector, home automation, online banking, and other industries. This study proposes a novel embedded system based curtain controlling unit using NRF module in response to the quickly expanding automation. The proposed system uses a NRF24L01 transceiver and an Atmega328p microcontroller to communicate via GPSK modulation. By pressing the switch on the rotary encoder, the user may control the motors (which are linked to the curtains). Above the OLED display, the curtain status is displayed. Given that the system employs a small chip CPU and a NRF24L01 transceiver using GPSK modulation for transmission, it is most likely designed for enabling low-power and wireless communication. This might be helpful in situations where running wires is difficult or impracticable in the areas like Auditoriums, Hospitals and old age homes, where mobility of humans remain as a major challenge.

关键词： Wireless communication Industries Wireless sensor networks Microcontrollers Hospitals Modulation Organic light emitting diodes

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：