检索结果-内蒙古大学图书馆

International conference on advanced Communication Technology (ICACT)

作者： Tieyan Chao Hui Liang Yuwei Ge Kai Hou xiang Dong Ting Peng Shaanxi Huashan Road and Bridge Group Co. LTD Xi'an Shaanxi Zhengcheng Road and Bridge Engineering Research Institute Co. LTD Xi'an Sichuan Chuanjiao Road and Bridge Co. LTD Sichuan Chang'an University Xi'an

This paper presents an IoT-based automated settlement monitoring system that aims to meet the diverse requirements of applications and the increasing demand for settlement monitoring. The system consists of a perception subsystem, data transmission layer, IoT cloud platform, and application terminal. The differential pressure static level sensor transmits the sensor serial port raw data to the 4G DTU through the RS-485 bus interface. Then, the 4G DTU converts it into a 4G network and transmits the data to the IoT cloud platform via the MQTT protocol. The IoT cloud platform analyzes and processes the collected data to generate reports, visualize data to generate curves, and perform real-time anomaly identification on the data. Finally, it implements viewing of settlement monitoring data and curve changes, as well as monitoring status warnings at the application terminal. The practical engineering application results show that this system can provide effective safety monitoring and an early warning scheme for slope, tunnel, bridge, and building safety monitoring.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Curving Motion Control of a Traction Rail Mover Using a Dual BLAC Motor Drive

引用

IEEE TRANSACTIONS ON INDUSTRY applications 2023年第1期59卷 1175-1183页

作者： Ok, Sangjae Bae, Jongnam Lee, Dong-Hee Kyungsung Univ Dept Mechatron Engn Busan 48434 South Korea

This article presents an improved position control method of an overhang-type rail system considering a curved path. The designed system is driven by two BLAC (brushless ac) motors, and the moving position is controlled based on the signal from a simple Hall position sensor mounted on the motor without any absolute position sensors. The rail is composed of both linear and curved paths. For the linear rail, the two motors are controlled to rotate in the same speed. However, in a curved path, the two motors must have different moving distance according to the curvature. Generally, in order to determine the proper motion commands for both traction motors, the actual curvature state and position have to be detected by a potentiometer or an encoder equipped with linear position sensor, but this method significantly increases complexity and cost of the system. This article aims to solve this problem by using a low-cost semiconductor IMU (inertia measurement unit) to estimate the actual rail condition. The IMU will then estimate the heading angle variation to compensate the motion commands for the two BLAC motors without any additional external absolute sensors. As a result, a balanced and improved motion can be achieved for an arbitrary rail path. Practical experiments using an overhang-type rail traction system were performed to verify the effectiveness of the proposed control scheme. The results show the advanced control performance in both linear and curved path, and also a smooth transition between them both.

关键词： Rails Traction motors Brushless motors AC motors Rotors Permanent magnet motors Synchronous motors Curving motion dual BLAC (brushless ac) motor Hall sensor heading angle estimation turning

来源：评论

学校读者我要写书评

暂无评论

Two-stage Amplifier Design for ECG Signal Processing 6

Two-stage Amplifier Design for ECG Signal Processing

引用

2023 IEEE 6th International conference on Information systems and Computer Aided Education, ICISCAE 2023

作者： Ma, Junyi Xi'an Jiaotong-Liverpool University School of Advanced Technology Suzhou215000 China

ISBN: (纸本)9798350313444

The electrocardiogram (ECG) is a widely used medical diagnostic tool for assessing the electrical activity of the heart. This study focuses on the signal processing aspect of ECG analysis, encompassing signal generation, filtering, amplification, and denoising. After investigating the generation of ECG signals, this passage applies a cascade of filtering techniques, including Low-pass Filtering, high-pass Filtering, and notch filters, to preprocess the acquired ECG signals. Subsequently, a two-stage amplifier is employed to enhance the weak ECG signals, making them more observable for subsequent analysis. To further improve the signal quality, denoising techniques such as Wavelet Denoising, Empirical Mode Decomposition, and Empirical Wavelet Transform are applied. The design and simulation of the two-stage amplifier using CoolSpice resulted in an 80 dB DC gain and a -3dB bandwidth of approximately 3 kHz, while maintaining a stable phase margin of approximately 50 degrees, ensuring reliable amplification. The favorable characteristics observed in the simulation results demonstrate the viability of integrating the two-stage amplifier into future ECG signal processing applications. © 2023 IEEE.

关键词： ECG signal Filter Phase Margin Two-stage Amplifier

来源：评论

学校读者我要写书评

暂无评论

Real-time Heart Rate Estimation Using PVDF Flexible Piezoelectric sensor Based on Machine Learning 2

Real-time Heart Rate Estimation Using PVDF Flexible Piezoele...

引用

2nd International conference on advanced Manufacturing Technology and Manufacturing systems, ICAMTMS 2023

作者： Luo, Shijian Fang, Ting Dong, Chong Han, Jiaming School of Electrical and Information Engineering Anhui University of Technology Anhui Ma’anshan243032 China Anhui Engineering Research Center for Intelligent Applications and Security of Industrial Internet Anhui University of Technology Anhui Ma’anshan243032 China

ISBN: (纸本)9781510667327

To achieve non-invasive, non-contact, and real-time heart rate monitoring, proposed a pulse signal acquisition system using PVDF (Polyvinylidene Fluoride) piezoelectric film. In order to address the issue of errors in heart rate extraction caused by differences in the morphology of pulse signals across individuals or in different states, the K-means clustering algorithm was innovatively used to locate the peak of pulse waveforms in different states and constructed a heart rate data set. Real-time heart rate monitoring by training a large number of pulse signal samples with the proposed CNN-LSTM network model. Experimental results demonstrated that the performance metrics of this model, including the MAE (Mean Absolute Error), RMSE (Root Mean Square Error), and R2(Coefficient of Determination), are 0.2517, 0.3395, and 0.9863, respectively. the maximum error between the proposed system and the standard instrument within 3 minutes was only 1.55 beats/minute, indicating that the system exhibits high accuracy and reliability, and holds great potential for applications in heart rate detection. © 2023 SPIE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning (ML)-Inspired Method for Intrusion Detection in IoT Devices Networks 5th

A Machine Learning (ML)-Inspired Method for Intrusion Detect...

引用

5th International conference on Computing Science, Communication and Security

作者： Venkatesh, Veeramuthu Raj, Pethuru Nedium, Roshitha Edara, Jahnavi Reddy, Kalluru Amarnath Anushiadevi, R. SASTRA Deemed Univ Sch Comp Thanjavur 613401 Tamilnadu India Reliance Jio Cloud Serv JCS Bangalore 560025 Karnataka India

ISBN: (纸本)9783031751691;9783031751707

The Internet of Things (IoT) and Machine Learning (ML) represent dynamic research fields with significant growth. IoT applications have gained popularity among technology researchers and developers, and the increasing deployment of IoT devices in critical infrastructures improves efficiency and reliability and raises concerns about cyber-attacks. Enterprises have effectively implemented IoT services, enabling automated production through remote and intelligent control. However, this adoption has concurrently introduced novel security vulnerabilities. Addressing the security and privacy challenges in IoT, especially considering energy limitations and scalability issues, remains a critical focus in computer security. This paper aims to prevent multiple attacks targeting sensor nodes' data manipulation. It encompasses a range of threats, such as sensing layer attacks, malfunctions, tamper attacks, false data injection, base node and clone attacks. The proposed approach involves a threat model and a pairing algorithm that utilizes machine learning to associate each sensor node with its corresponding node. To accomplish the goal, the performance of the proposed solution is compared with various machine learning models, including Decision Tree, Linear Regression, k-nearest neighbors (KNN), Random Forest, and AdaBoost. The evaluation utilized two openly accessible real-world datasets, with metrics such as accuracy in attack detection, training time, and testing time being considered. By incorporating machine learning algorithms to improve attack detection in IoT environments, the proposed approach represents a significant advancement in enhancing security and privacy. The results highlight the importance of adopting advanced techniques to safeguard IoT systems from potential threats. The proposed method achieved an impressive 96.75% accuracy rate in detecting attacks, surpassing existing solutions with nearly twice the speed in training and testing times. As the IoT landsc

关键词： sensor nodes Security attacks Intrusion Detection System Critical infrastructure Machine learning Internet of Things (IoT)

来源：评论

学校读者我要写书评

暂无评论

The applications of the PHM in INS Area 5th

The Applications of the PHM in INS Area

引用

5th China Aviation Science and Technology conference, 2021

作者： Hanping, Wang xiaotang, Lian Zhao, Liu Department of Navigation Xi’an Flight Automatic Control Research Institute Xi’an710061 China Department of Test Flight Test and Research Institute Xi’an710089 China

ISBN: (纸本)9789811674228

PHM is an effective technique of which can advance the capability of the colligating Fault Diagnosis and reduce the use and the RMS (Reliability maintainability Security) fee of the government equipment. By absorbing the advanced overseas experience, PHM is embedded researched. It is combined the idiographic points of INS, and confirmed frame of PHM. The INS fault prognosis model which is based on PHM is proposed in the paper. It is detailedly expatiated on the INS PHM method, and take an example about the key circuits in INS to explain the scenario of the PHM. At last, it is expatiated the manage points about PHM in INS area. By the applications of the system, it is a large right-about change about the INS (Inertia navigation system) maintenance methods, viz. from the traditional Diagnosis method which based on the sensor to the prognosis method which based on the intellectualized system and from the afterwards or time-lapse maintain to the maintain method which based on the state maintain. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

A Hybrid framework for mobile augmented reality 9

A Hybrid framework for mobile augmented reality

引用

9th International conference on advanced Cloud and Big Data, CBD 2021

作者： Zhang, Shaobo Zhao, Wanqing Zhao, Yan Peng, xianlin Peng, Jinye Northwest University School of Information Science and Technology Xi'an China Northwest University Art School Xi'an China

ISBN: (纸本)9781665407458

Augmented reality (AR) aims to combine real and virtual worlds, offering real-time 3D interactions between users and virtual information. Existed AR systems detect specific markers in environments and augmented them with virtual contents such as 3D objects and videos. With the explosive growth of powerful, less expensive mobile devices, AR systems are extended to mobile devices. However, they fail to achieve the accurate and real-time integration of the real world and virtual contents because of the insufficient detection accuracy to objects in real world and computational resource shortage. In this paper, we propose a hybrid AR framework that integrates cloud computing, 5G communication and deep learning technology to achieve accurate tracking and ultra-low latency mobile AR applications. Our AR framework contains three blocks, an image capturing block, a deep learning based objects tracking block and a WebGL based rendering block. We use cloud computing technology to deploy them on mobile devices and a cloud server separately according to calculation amounts and use 5G to achieve communication between the cloud server and mobiles devices. The experiment results show that the accuracy and running speed of our framework can meet the requirements of most mobile AR applications. © 2022 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Multi-sensor Ensemble-guided Attention Network for Aerial Vehicle Perception Beyond Visible Spectrum

Multi-sensor Ensemble-guided Attention Network for Aerial Ve...

引用

IEEE/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Kwasniewska, Alicja MacAllister, Anastacia Nicolas, Rey Garza, Javier SiMa Technol 226 Airport Pkwy San Jose CA 95110 USA Gen Atom 14200 Kirkham Way Poway CA 92064 USA Lockheed Martin 1 Lockheed Blvd Ft Worth TX 76108 USA

ISBN: (纸本)9798350302493

Researchers from different market domains have made significant developments in Artificial Intelligence (AI) enabling more advanced automated sensing systems and, thus, eliminating the need for the time-consuming manual analysis of data, which is prone to human errors. However, successful deployment of such systems in real world applications requires careful design and analysis of the proposed models. This work focuses on perception done on Unmanned Aerial Vehicles (UAV) using multi-task learning. There are multiple challenges when considering such platforms. First of all, they often operate in difficult and dynamic conditions affected by various factors, such as background noises, ego-noise of the motors and occluded views. At the same time, they require high performance local compute, co-designed with optimized software solutions that meet small size, weight, and power (SWaP) requirements. Therefore, the AI models designed for such systems should not introduce computational and memory overheads to allow for real time processing at the embedded edge. Taking this into account, this work proposes a novel neural network-based system that utilizes ensemble-guided modulations of audio path fused with the infrared (IR) visual embedding using the attention mechanism. The ensemble mechanism doesn't require spawning new ensemble members, but instead operates on FiLM (Feature-wise Linear Modulation) activation, making it suitable for resource-constraints embedded edge platforms. The performed experiments show that the proposed network outperforms a single FiLM network by 15% and is more robust to noise.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Optimization of Energy Demand Management in Cold Storage systems: Advances through the Integration of IoT, Machine Learning, and AI

Optimization of Energy Demand Management in Cold Storage Sys...

引用

2024 IEEE Latin American conference on Computational Intelligence, LA-CCI 2024

作者： Salgado, Robinson Alvarado, Gaddiel Loo, Luis Universidad Tecnológica de Honduras Maestría en Automatización Industrial Tegucigalpa Honduras Universidad Tecnológica de Honduras Escuela de Postgrado San Pedro Sula Honduras

ISBN: (纸本)9798350374575

Cold storage facilities play a crucial role in preserving perishable products across various industries, including food, pharmaceuticals, and agriculture. The high energy consumption of refrigeration systems in these facilities necessitates efficient energy management. This article uses Long Short-Term Memory (LSTM) models in a novel way to predict temperature and power demand variations in cold storage systems, leading to more accurate forecasts. The research improves demand response applications and achieves significant energy savings through real-world deployment by combining real-Time IoT sensor data and deep learning. The study provides scalable framework that can be applied to a variety of industrial settings, helping to promote more sustainable energy management practices by optimizing power usage and lowering operational costs. Various methodologies and models were evaluated to predict and manage temperature variations and energy demand efficiently. The results demonstrate significant enhancements in energy efficiency, reduced energy consumption, and optimized resource usage. Among the evaluated machine learning techniques, deep neural networks, specifically Long Short-Term Memory (LSTM) models, showed superior accuracy and responsiveness. Mini-ROCKET and DrCIF, along with their precision and lower mean absolute error (MAE), make reliable predictions possible with a MAPE below 0.2 having overall accuracy of this model is 96%. Additionally, the adaptability of these models to abrupt operational changes was analyzed, highlighting their advantages and limitations. The paper concludes with recommendations for future research and development, promoting the adoption of advanced and sustainable technologies in energy management for cold storage systems. © 2024 IEEE.

关键词： Demand response

来源：评论

学校读者我要写书评

暂无评论

Routing Protocols in Wireless sensor Networks: A Comprehensive Review and Future Perspectives 7

Routing Protocols in Wireless Sensor Networks: A Comprehensi...

引用

7th International conference on Contemporary Computing and Informatics, IC3I 2024

作者： Kaur, Puneet Kaur, Kiranbir Verma, Deepak Kumar Singh, Kuldeep Kaushik, Keshav Singh, Vineeta Guru Nanak Dev University Department of Computer Engineering & Technology Punjab Amritsar India Department of Computer Science and Engineering Uttar Pradesh Kalyanpur India Guru Nanak Dev University Department of Electronics Technology Punjab Amritsar India Amity University Amity School of Engineering and Technology Punjab Mohali India

ISBN: (纸本)9798350350067

Wireless sensor Networks (WSNs) have significantly transformed diverse domains such as industrial automation, healthcare, disaster management, and environmental monitoring. The complex interaction of routing protocols, essential for enabling smooth data transport despite the specific difficulties in WSN environments, is the core of their success. The objective of this study is to get a accurate understanding of routing algorithms specifically projected for wireless sensor networks. Expanding upon the essential features and significant disputes faced in WSN systems, admitting limited energy resources, bandwidth constraints, and node processing capabilities, the discussion accentuates the significance of effective routing protocols. Furthermore, it thoroughly analyzes many forms of routing protocols, including basic hierarchical and flat schemes, as well as advanced location-based and data-centric protocols. The protocol category is thoroughly examined, uncovering its unique benefits, limitations, and suitability for various WSN applications. Furthermore, the review reveals the latest developments and upcoming trends in WSN routing protocols, brooding areas such as energy efficiency, dependability, scalability, and adaptive resilience to changing network considerations. In conclusion, the evaluation furnishes a forward-looking view by outlining potential research areas and possible pathways for meliorating the designs of WSN routing protocols. The main goal is to heighten the efficacy and practicality of WSNs. In this work, we examined a number of routing algorithms according to important criteria including mobility, scalability, energy efficiency, and Quality of Service (QoS). We looked at how each method handles node mobility, performs as the network expands, guarantees dependable data transmission, and optimizes energy use. We also looked at ways for choosing the cluster head (CH), energy-saving data aggregation strategies, redundancy-reduction mechanisms, and the

关键词： Routing algorithms

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：