检索结果-内蒙古大学图书馆

13th IEEE Global conference on Consumer Electronic, GCCE 2024

作者： Tseng, Chien-Cheng Lee, Su-Ling National Kaohsiung University of Science and Technology Department of Computer and Communication Engineering Kaohsiung Taiwan Chang Jung Christian University Department of Computer Science and Information Engineering Tainan Taiwan

ISBN: (纸本)9798350355079

The utilization of sensor networks for collecting climate-related data, encompassing temperature, rainfall, pressure, and wind measurements, has become widespread in endeavors to understand climate change. Typically, these data are depicted through an irregular graph model, where each sensor corresponds to a vertex, and edges denote similarity relations between sensors, with the measured data at each vertex represented as graph signals. However, a notable challenge in sensor networks stems from potential data gaps due to sensor malfunctions or communication failures, necessitating the development of methods to accurately estimate missing signal values. This paper addresses this challenge by introducing a method for recovering missing data. Initially, it defines the fractional graph Fourier transform (FrGFT) of irregular data and utilizes the bandlimitedness property of FrGFT to devise a missing data recovery approach. Subsequently, it investigates the relationship between recovery error and fractional order to pinpoint the optimal fractional order that minimizes recovery error. Finally, the efficacy of the proposed FrGFT method is demonstrated using temperature data collected by a sensor network in the USA. Additionally, a performance comparison with the conventional graph Fourier transform (GFT) method is conducted to highlight the superiority of the proposed approach. © 2024 IEEE.

关键词： graph Fourier transform graph signal processing missing data recovery sensor network

来源：评论

学校读者我要写书评

暂无评论

An intelligent Fusion of Machine Learning and Optimization for Performance Improvisation in Wireless sensor networks 7

An Intelligent Fusion of Machine Learning and Optimization f...

引用

7th International conference on Image information processing, ICIIP 2023

作者： Thakur, Puja Sidhu, Jagpreet Kanwar, Kushal Cse Juit Solan Waknaghat India Stme Nmims Chandigarh Chandigarh India

ISBN: (纸本)9798350371406

In present days, Wireless sensor networks (WSNs) have become a significant scientific advancement with a wide range of applications, spanning from environmental monitoring to industrial automation. However, the obstacles presented by restricted resources of energy, ever-changing settings, and fluctuating communication situations require inventive strategies to optimize their effectiveness. This work introduces a novel integration of machine learning and optimization methodologies with the objective of enhancing the efficiency of WSNs. Here, we used the concept of a Clustering-based routing mechanism with the Cuckoo Search Algorithm (CSA) and Neural Network (NN) as a machine learning approach. This work aims to examine the incorporation of machine learning techniques and optimization methodologies in order to tackle the complex issues encountered by WSNs. The evaluation of the suggested methodology in comparison to standard methodologies involves the utilization of performance measures such as energy consumption, network lifetime, and packet delivery ratio. The findings indicate significant improvements in energy efficiency, network stability, and data throughput, hence confirming the effectiveness of the integrated approach using machine learning and optimization. © 2023 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of fire alarm module for smart home

Design and implementation of fire alarm module for smart hom...

引用

2023 International conference on Electronic information Engineering and Data processing, EIEDP 2023

作者： Liu, Xiaohong Yan, Kai College of Big Data and Intelligent Engineering Southwest Forestry University Kunming650224 China Key Laboratory of Metallurgical Equipment and Control Technology Ministry of Education Wuhan University of Science and Technology Wuhan430081 China

ISBN: (纸本)9781510666160

With the continuous development of information technology, artificial intelligence fire automatic alarm system is gradually developed. However, the current system is based on a single sensor for identification, when a fire still uses manual active fire extinguishing, low efficiency in handling fire, high failure rate, poor system scalability, poor anti-interference ability, high false alarm rate. At the same time, the recognition accuracy is low, the processing speed and intelligence are also insufficient. Therefore. To address the above problems, this study designs a multi-sensor artificial intelligence fire prevention system using smoke and temperature sensors. The fire prevention system can send alarm signals at the earliest stage of fire and can intelligently extinguish the fire, so that the disaster can be controlled and extinguished by taking measures in advance. Meanwhile, the system can continue to work even if one of the sensors is not working properly. © 2023 SPIE.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

A Distributed Acoustic sensor System for intelligent Transportation using Deep Learning

引用

IEEE Internet of Things Magazine 2024年第5期7卷 88-96页

作者： Chiang, Chia-Yen Zhong, Ruikang Jaber, Mona Hayward, Peter Queen Mary University of London United Kingdom T2 Sensing United Kingdom

intelligent transport systems (ITS) are pivotal in the development of sustainable and green urban living. ITS is data-driven and enabled by the profusion of sensors ranging from pneumatic tubes to smart cameras. This work explores a novel data source based on optical fibre-based distributed acoustic sensors (DAS) for traffic analysis. Detecting the type of vehicle and estimating the occupancy of vehicles are prime concerns in ITS. The first is motivated by the need for tracking, controlling, and forecasting traffic flow. The second targets the regulation of high occupancy vehicle lanes in an attempt to reduce emissions and congestion. These tasks are often conducted by individuals inspecting vehicles or through the use of emerging computer vision technologies. The former is not scale-able nor efficient whereas the latter is intrusive to passengers' privacy. To this end, we propose a deep learning technique to analyse DAS signals, which are correlated to the weight and other physical features of vehicles, to achieve load detection through continuous sensing with privacy protection. We propose a deep learning method for processing DAS signals, achieving 86% vehicle classification accuracy and 94-98% in occupancy detection based on DAS data collected under controlled conditions. © 2018 IEEE.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

A Deep Multi-Task Learning Network for Activity Recognition and User Identification Using Smartphone sensors 16

A Deep Multi-Task Learning Network for Activity Recognition ...

引用

16th International conference on ENTERprise information Systems, CENTERIS 2024 - 12th International conference on Project MANagement, ProjMAN 2024 - 14th International conference on Health and Social Care information Systems and Technologies, HCist 2024

作者： Mekruksavanich, Sakorn Phaphan, Wikanda Jitpattanakul, Anuchit Department of Computer Engineering School of Information and Communication Technology University of Phayao Phayao56000 Thailand Research Group in Statistical Learning and Inference Department of Applied Statistics Faculty of Applied Science King Mongkut's University of Technology North Bangkok Bangkok10800 Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science King Mongkut's University of Technology North Bangkok Bangkok10800 Thailand

Human activity recognition (HAR) and user identification utilizing smartphone sensors are crucial in domains such as wellness tracking, tailored services, and security. Conventional approaches handle these activities as distinct entities, leading to less-Than-ideal performance and restricted applicability. This research presents a novel deep multi-Task learning network that simultaneously performs activity recognition and user identification using smartphone sensor data. By leveraging shared representations and task-specific information, the network enhances accuracy. It combines a shared convolutional neural network (CNN) with bidirectional long short-Term memory (BiLSTM) layers to extract features from raw sensor data. The CNN identifies patterns, while the BiLSTM captures sequential dependencies and contextual information. These features are processed by fully connected layers for both activity recognition and user identification. A multi-Task loss function is proposed to optimize both tasks based on their complexity and importance. The approach is tested on the UCI-HAR dataset, containing diverse activities from multiple users. Experimental results show that the proposed CNN-BiLSTM model achieves 97.64% accuracy in activity recognition and 82.59% in user identification, surpassing current state-of-The-Art methods. This demonstrates the effectiveness of the multi-Task learning framework and the advantage of using the shared CNN-BiLSTM architecture for improving both tasks. © 2025 The Author(s).

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Problems of Building Digital Twins of Escalators at Subway Stations Based on Machine Learning

Problems of Building Digital Twins of Escalators at Subway S...

引用

Computing conference

作者： Subbotin, Alexey Zhukova, Nataly Gudilov, Mikhail St Petersburg State Electrotech Univ St Petersburg Russia Russian Acad Sci St Petersburg Inst Informat & Automat St Petersburg Russia

ISBN: (纸本)9783031622717;9783031622694;9783031622687

This article discusses the main problems that arise when constructing digital twins (DT) as models of the subway stations and their elements based on data processing using machine learning methods. The subject area is considered and shortcomings are identified in the applied methods for constructing digital twins when information is provided by several sources of various types: video cameras, microphones, sensors. The problems of rebuilding digital twins when new information arrives are discussed. To ensure the possibility of building and rebuilding DTs, it is proposed to use the development environment Xcode and operation system macOS, as their usage allows reduce the time for building and rebuilding models, and to use built-in libraries from Apple, which make it possible to significantly simplify data processing based on machine learning tools. In the proposed solution, the construction and reconstruction of digital twins is carried out on Apple chips M2 and M1, data processing is performed by Apple libraries on the RISC-M2 chip. The increase in performance is 45.9%, the accuracy of event identification increases by 15.3%. The proposed solution can be applied not only in the discussed subject area, but also in building highly loaded systems, such as natural gas buses, trolleybuses, trams, commuter trains and subways were high speed of operation of monitoring systems of large objects with complex structure and behavior are required.

关键词： Digital twin Machine learning information processing RISC processors Non-Standard architecture computers Fog computing environments Multi-layer data center structure

来源：评论

学校读者我要写书评

暂无评论

Autonomous Multi-sensor Fusion Techniques for Environmental Perception in Self-Driving Vehicles

Autonomous Multi-Sensor Fusion Techniques for Environmental ...

引用

2024 International conference on Communication, Computer Sciences and Engineering, IC3SE 2024

作者： Sumalatha, I.P.P.A. Chaturvedi, Prateek Gowtham Raj, R. Patil, Shruti Thethi, H. Pal Hameed, Ali Abduhussien Institute Of Aeronautical Engineering Dundigal Hyderabad India Amity University Department Of Mechanical Engineering Greater Noida India New Horizon College Of Engineering Department Of Mechanical Engineering Bangalore India Mlr Institute Of Technology Department Of Information Technology Telangana Hyderabad India Lovely Professional University Phagwara India College Of Medical Technology The Islamic University Radiology Techniques Department Najaf Iraq

ISBN: (纸本)9798350366846

Assuming strong environmental awareness, the arrival of autonomous vehicles signals a revolutionary age in transportation. In order for autonomous vehicles to have trustworthy perception, this study explores the complex field of autonomous multi-sensor fusion methods. It highlights how different types of sensors, such as LiDAR, radar, and cameras, may work together to provide more complete and accurate environmental data. Examining the relative merits and practicality of early, late, and deep fusion, the article methodically investigates the several sensor fusion systems and how they fare in complicated and dynamic driving situations. The adaptive fusion technique, which improves detection and classification accuracy and optimizes computational resources by dynamically adjusting to ambient variables, is a novel component of this study. intelligent data integration and interpretation from sensors is the goal of this strategy, which makes use of machine learning techniques like recurrent neural networks and convolutional neural networks. Results show that the suggested method outperforms the state-of-the-art when compared to well-known benchmarks in terms of accuracy, reliability, and computing efficiency. In addition, this study emphasizes the important problems and potential solutions related to multi-sensor fusion, including handling data that is not updated in real-time, overcoming bad weather, and guaranteeing the ability to analyze data in real-time. To realize self-driving vehicles' full potential and create smarter, more efficient transportation networks, the results show how crucial new fusion techniques are. © 2024 IEEE.

关键词： Adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

Agricultural Automated Greenhouse Environmental Monitoring and Control Model Based on the Internet of Things and intelligent Algorithms

Agricultural Automated Greenhouse Environmental Monitoring a...

引用

2024 International conference on Power, Electrical Engineering, Electronics and Control, PEEEC 2024

作者： Guoxin, Han Huan, Dong Jing, Wu Suyan, Che Suijie, Zhong School of Information City College of Huizhou Huizhou516025 China School of Finance and Economics City College of Huizhou Huizhou516025 China School of Tourism and Cooking City College of Huizhou Huizhou516025 China School of Art and Design City College of Huizhou Huizhou516025 China

ISBN: (纸本)9798350378917

Huizhou is adjacent to Hong Kong, connected with Shenzhen, Dongguan and Guangzhou, with convenient land and water transportation, and its unique geographical position provides favorable conditions for commodity agriculture, intelligent computing technology is used to analyze and process information, so as to improve the perception of the real environment and realize intelligent decision-making and control, Agricultural Internet of Things is a combination of agricultural applications and Internet of Things technology, In many scenarios, actuators and sensors are relatively far away, As an object, it provides the most suitable growth environment such as temperature, humidity, light, water and fertilizer, so that crops can be in the best growth state, thus obtaining an efficient agriculture with high yield and high quality, However, compared with its application potential, Internet of Things technology still faces some important problems and challenges in agricultural automation, Comprehensive monitoring before and after planting has been achieved to make agricultural production increasingly efficient and high-quality, Agricultural greenhouse wireless sensor networks typically require the deployment of a large number of small sensor nodes, which are powered by small batteries with limited power, Therefore, in the new situation, reasonable adjustment of crop layout is the key to developing agricultural economy and cooperating with the construction of modern Huizhou. © 2024 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Research on intelligent Monitoring and Maintenance System of Power Grid Equipment Online Status under Internet of Things Platform Technology 3

Research on Intelligent Monitoring and Maintenance System of...

引用

3rd IEEE International conference on Electrical Engineering, Big Data and Algorithms, EEBDA 2024

作者： Chen, Wenkang Shi, Zhanquan Kang, Le Ni, Yi Xie, Fei Sichuan Sgit Technology Co. Ltd. Chengdu China State Grid Sichuan Electric Power Company Chengdu China

ISBN: (纸本)9798350380989

The existing power grid fault information acquisition methods are inefficient, slow and inaccurate, which are difficult to adapt to the growing demand of the power grid in the Internet of Things environment. In order to realize the intelligent monitoring and management of large-scale power equipment, the paper can start from the sensor level of the network, and use front-end sensors and ZigBee wireless line networking to complete the collection, aggregation and upload of information. This paper designs a power grid equipment fault monitoring system which is suitable for power grid monitoring. The circuit reset diagram is designed accordingly. According to the characteristics of wide distribution of data collection, the software function model to ensure the accuracy of data collection is established. The experimental results show that the fault information acquisition system can realize a large number of processing. © 2024 IEEE.

关键词： device online status fault information collection Internet of Things monitoring and maintenance

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection in IoT networks Based on intelligent Security Event Correlation 16

Anomaly Detection in IoT Networks Based on Intelligent Secur...

引用

16th International conference on COMmunication Systems and networks, COMSNETS 2024

作者： Kotenko, Igor Levshun, Diana Saint-Petersburg Russia

ISBN: (纸本)9798350383119

Modern Internet of Things networks combine many devices and sensors that transmit and process large amounts of data. Security tools identify security events that contain information about detected system or network states. In turn, high-performance data anomaly detection methods are required to ensure stability and reliability of work processes. information about the correlation of identified security events can be used to detect and explain deviations from normal states. This study proposes an anomaly detection approach based on the causal correlation of security events using machine learning. The proposed approach does not require prior knowledge of event scenarios. Using cluster analysis and a convolutional recurrent neural network, we construct a security state correlation graph corresponding to the normal behavior of the system. Cluster analysis determines the similarity of events to each other. A convolutional LSTM, analyzes the spatio-temporal relationship of events. Using the identified event correlation thresholds, we look for anomalies in real time. Experimental results on an Internet of Things sensor dataset show that the proposed method is efficient in anomaly detection tasks. © 2024 IEEE.

关键词： anomaly detection cybersecurity event correlation Internet of things machine learning

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：