Due to the influence of sea conditions, six dimensional movements, including heave, roll, pitch, sway, surge and yaw, are easy to be produced while ships sailing. These motions seriously affect the safety of its sailing, so the prediction of ship motion attitude is particularly important. In this case, a new combined model called CWGRU is proposed for predicting ship motion attitude with high accuracy. The CWGRU is based on complete ensemble empirical mode decomposition algorithm (CEEMD), whale optimization algorithm (WOA) and gated recurrent unit (GRU). Firstly, the CEEMD algorithm is used to decompose the ship’s sailing attitude data into a number of intrinsic mode functions (IMF) with different characteristics, so that the non-stationary time sequences have stability and periodicity. Then, the GRU based on WOA (WGRU) model is used to learn the short-term characteristics of each IMF component and predict it. Finally, the predicted values of each IMF component are added to obtain the prediction results. In order to verify the effectiveness of the CWGRU model proposed in this paper, the experiment based on real motion data collected in a ship are carried out. The first 80 of the data is used as the training set, and the last 20 is used for the test. Experimental results show that the performance of CWGRU is much better than that of GRU and WGRU.
{"title":"Prediction of Ship Motion Attitude Based on Combined Model","authors":"Xingyuan Liu, Xiandeng He, Yu-sheng Yi","doi":"10.1145/3585967.3585991","DOIUrl":"https://doi.org/10.1145/3585967.3585991","url":null,"abstract":"Due to the influence of sea conditions, six dimensional movements, including heave, roll, pitch, sway, surge and yaw, are easy to be produced while ships sailing. These motions seriously affect the safety of its sailing, so the prediction of ship motion attitude is particularly important. In this case, a new combined model called CWGRU is proposed for predicting ship motion attitude with high accuracy. The CWGRU is based on complete ensemble empirical mode decomposition algorithm (CEEMD), whale optimization algorithm (WOA) and gated recurrent unit (GRU). Firstly, the CEEMD algorithm is used to decompose the ship’s sailing attitude data into a number of intrinsic mode functions (IMF) with different characteristics, so that the non-stationary time sequences have stability and periodicity. Then, the GRU based on WOA (WGRU) model is used to learn the short-term characteristics of each IMF component and predict it. Finally, the predicted values of each IMF component are added to obtain the prediction results. In order to verify the effectiveness of the CWGRU model proposed in this paper, the experiment based on real motion data collected in a ship are carried out. The first 80 of the data is used as the training set, and the last 20 is used for the test. Experimental results show that the performance of CWGRU is much better than that of GRU and WGRU.","PeriodicalId":275067,"journal":{"name":"Proceedings of the 2023 10th International Conference on Wireless Communication and Sensor Networks","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121570576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Artificial intelligence internet of things (AIoT) is a technology that came into being under the development of artificial intelligence (AI) and Internet of things (IOT) where deep learning is vigorously promoted and used. Compared with the traditional concept of the Internet of things, the main difference of AIoT technology is that it applies interconnected devices which are embedded with the capacity of neural network model reasoning to the perception layer, this reduce reliance on edge servers (especially for neural network model training or reasoning). Thus, the edge devices of the system will get a more intelligent execution power. For the IOT system structures that have been built at present, most of the interconnection devices in the sensing layer, such as data acquisition nodes or execution nodes, are designed with the low and medium performance microcontroller unit as the processing core. After using the technology such like lightweight neural network and global average pooling, we succeed in deploying the convolutional neural network model to the low and medium performance microcontroller. Thus, the original node can get the reasoning result of neural network model in offline state and use it as a decision element for the operation of the system whit a simple modification of the program.
{"title":"A research of convolutional neural network model deployment in low- to medium-performance microcontrollers","authors":"Jingtao Guan, Guihuang Liang","doi":"10.1145/3585967.3585975","DOIUrl":"https://doi.org/10.1145/3585967.3585975","url":null,"abstract":"Artificial intelligence internet of things (AIoT) is a technology that came into being under the development of artificial intelligence (AI) and Internet of things (IOT) where deep learning is vigorously promoted and used. Compared with the traditional concept of the Internet of things, the main difference of AIoT technology is that it applies interconnected devices which are embedded with the capacity of neural network model reasoning to the perception layer, this reduce reliance on edge servers (especially for neural network model training or reasoning). Thus, the edge devices of the system will get a more intelligent execution power. For the IOT system structures that have been built at present, most of the interconnection devices in the sensing layer, such as data acquisition nodes or execution nodes, are designed with the low and medium performance microcontroller unit as the processing core. After using the technology such like lightweight neural network and global average pooling, we succeed in deploying the convolutional neural network model to the low and medium performance microcontroller. Thus, the original node can get the reasoning result of neural network model in offline state and use it as a decision element for the operation of the system whit a simple modification of the program.","PeriodicalId":275067,"journal":{"name":"Proceedings of the 2023 10th International Conference on Wireless Communication and Sensor Networks","volume":"482 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115084403","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yujiao Wang, Haiyun Lin, Chunyu Li, L. She, Li Sun, Junwei Wang
The network autonomous learning monitoring system is a subsystem of the learning quality monitoring system in the network education platform. Based on the training objectives of network education and the course learning objectives of learners, and on the basis of educational evaluation theory, it makes value judgments on learners' attitudes, knowledge and ability development level in the whole learning process. Through the planning, inspection, evaluation, feedback, control and adjustment of learners' learning activities, timely guide learners to correct their learning attitude, adjust their learning strategies, and effectively use learning resources and modern information technology means to carry out autonomous learning, so as to achieve the expected learning goals. The network self-learning monitoring system is based on the database created by SQL Server platform, supports C/S structure, has good scalability and usability, and is used to extract and analyze data. SVM algorithm is used to extract system features, which has the advantages of low system load, low response delay and good performance. An accurate network autonomous learning monitoring system model is constructed. After system test, the network autonomous learning monitoring system based on SVM algorithm has high data analysis ability, easy to understand, easy to maintain, reasonable structure and easy to use, which meets the needs of learners. Using SVM algorithm for feature extraction, the evaluation performance of the algorithm is improved by more than 3.2%. When learners learn in the system, the system load is small, the response delay is low, and the performance is good. It is an accurate network autonomous learning monitoring system.
{"title":"Network Autonomous Learning Monitoring System Based on SVM Algorithm","authors":"Yujiao Wang, Haiyun Lin, Chunyu Li, L. She, Li Sun, Junwei Wang","doi":"10.1145/3585967.3585984","DOIUrl":"https://doi.org/10.1145/3585967.3585984","url":null,"abstract":"The network autonomous learning monitoring system is a subsystem of the learning quality monitoring system in the network education platform. Based on the training objectives of network education and the course learning objectives of learners, and on the basis of educational evaluation theory, it makes value judgments on learners' attitudes, knowledge and ability development level in the whole learning process. Through the planning, inspection, evaluation, feedback, control and adjustment of learners' learning activities, timely guide learners to correct their learning attitude, adjust their learning strategies, and effectively use learning resources and modern information technology means to carry out autonomous learning, so as to achieve the expected learning goals. The network self-learning monitoring system is based on the database created by SQL Server platform, supports C/S structure, has good scalability and usability, and is used to extract and analyze data. SVM algorithm is used to extract system features, which has the advantages of low system load, low response delay and good performance. An accurate network autonomous learning monitoring system model is constructed. After system test, the network autonomous learning monitoring system based on SVM algorithm has high data analysis ability, easy to understand, easy to maintain, reasonable structure and easy to use, which meets the needs of learners. Using SVM algorithm for feature extraction, the evaluation performance of the algorithm is improved by more than 3.2%. When learners learn in the system, the system load is small, the response delay is low, and the performance is good. It is an accurate network autonomous learning monitoring system.","PeriodicalId":275067,"journal":{"name":"Proceedings of the 2023 10th International Conference on Wireless Communication and Sensor Networks","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116341433","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
H. Shang, Ruifeng Chen, Guoyu Ma, Haoxiang Zhang, R. He, B. Ai, Z. Zhong
With the rapid development of high-speed railways, intelligent railways have attracted much attention in railway industries and research institutes all over the world. The internet of things for railways (IoT-R) plays an important role for intelligent railways. In order to use limited radio resources to support massive low-cost and low-energy users in IoT-R, advanced multiple access technology becomes important. Tandem spreading multiple access (TSMA) is a recently proposed non-orthogonal multiple access scheme that uses a non-iterative receiver to solve the problem of data collision. In addition, TSMA can improve data transmission reliability and user connection capability at the expense of user data rate. Therefore, TSMA shows its potential in IoT-R. However, IoT-R has high requirements for data transmission reliability. In order to further improve data transmission reliability in IoT-R, TSMA with polar code system is proposed in this paper. Different from channel pre-compensation method used in the original TSMA system, the least squares channel estimation is applied in TSMA with polar code system. In addition, zero-forcing (ZF) equalizer and minimum mean square error (MMSE) equalizer are applied in TSMA with polar code system. Simulation results show that block error rate of TSMA with polar code system in both additive white Gaussian noise channel and Rayleigh fading channel is lower than that of TSMA system. In addition, TSMA with polar code system using MMSE equalizer has better performance than TSMA with polar code system using ZF equalizer.
{"title":"Performance Evaluation of Tandem Spreading Multiple Access with Polar Code System for IoT-Railways","authors":"H. Shang, Ruifeng Chen, Guoyu Ma, Haoxiang Zhang, R. He, B. Ai, Z. Zhong","doi":"10.1145/3585967.3585972","DOIUrl":"https://doi.org/10.1145/3585967.3585972","url":null,"abstract":"With the rapid development of high-speed railways, intelligent railways have attracted much attention in railway industries and research institutes all over the world. The internet of things for railways (IoT-R) plays an important role for intelligent railways. In order to use limited radio resources to support massive low-cost and low-energy users in IoT-R, advanced multiple access technology becomes important. Tandem spreading multiple access (TSMA) is a recently proposed non-orthogonal multiple access scheme that uses a non-iterative receiver to solve the problem of data collision. In addition, TSMA can improve data transmission reliability and user connection capability at the expense of user data rate. Therefore, TSMA shows its potential in IoT-R. However, IoT-R has high requirements for data transmission reliability. In order to further improve data transmission reliability in IoT-R, TSMA with polar code system is proposed in this paper. Different from channel pre-compensation method used in the original TSMA system, the least squares channel estimation is applied in TSMA with polar code system. In addition, zero-forcing (ZF) equalizer and minimum mean square error (MMSE) equalizer are applied in TSMA with polar code system. Simulation results show that block error rate of TSMA with polar code system in both additive white Gaussian noise channel and Rayleigh fading channel is lower than that of TSMA system. In addition, TSMA with polar code system using MMSE equalizer has better performance than TSMA with polar code system using ZF equalizer.","PeriodicalId":275067,"journal":{"name":"Proceedings of the 2023 10th International Conference on Wireless Communication and Sensor Networks","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130580492","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract—With the development of smart devices, Internet of Things(IoT) has requirements for high coverage, high reliability, and low power consumption for wireless communication systems. The emergence of reconfigurable intelligent surfaces(RIS) provides an achievable solution for further development of IoT. RIS consists of passive low-cost components, which can reshaping the wireless channel. Thus it can improve multi-stream transmission gain, enhance edge coverage and realize large-scale Device-to-Device communication. In this paper, we consider RIS-assisted multiple-input single-output(MISO) communication systems, and our goal is to maximize the sum-rate of all IoT receiving devices by jointly designing the beamforming of access points(AP) and the phase shift of RIS elements. For the non-convex problem form, we propose the Improved Elite Genetic Algorithm(IEGA) to obtain a smooth solution of the problem. Numerical results demonstrate the effectiveness of RIS and the proposed joint algorithm for the performance improvement of IoT wireless communication systems.We analyzed the impact of the deployment of RIS and the number of RIS elements on the sum-rate at the receiving devices, which facilitates the balance between the cost and benefit of increasing RIS elements in practical deployments.
{"title":"Sum-rate Maximization for RIS-assisted IoT","authors":"Zicheng Xing, Yunhui Yi, Xiandeng He, Junwei Chai, Yuanxinyu Luo, Xingcai Zhang","doi":"10.1145/3585967.3585974","DOIUrl":"https://doi.org/10.1145/3585967.3585974","url":null,"abstract":"Abstract—With the development of smart devices, Internet of Things(IoT) has requirements for high coverage, high reliability, and low power consumption for wireless communication systems. The emergence of reconfigurable intelligent surfaces(RIS) provides an achievable solution for further development of IoT. RIS consists of passive low-cost components, which can reshaping the wireless channel. Thus it can improve multi-stream transmission gain, enhance edge coverage and realize large-scale Device-to-Device communication. In this paper, we consider RIS-assisted multiple-input single-output(MISO) communication systems, and our goal is to maximize the sum-rate of all IoT receiving devices by jointly designing the beamforming of access points(AP) and the phase shift of RIS elements. For the non-convex problem form, we propose the Improved Elite Genetic Algorithm(IEGA) to obtain a smooth solution of the problem. Numerical results demonstrate the effectiveness of RIS and the proposed joint algorithm for the performance improvement of IoT wireless communication systems.We analyzed the impact of the deployment of RIS and the number of RIS elements on the sum-rate at the receiving devices, which facilitates the balance between the cost and benefit of increasing RIS elements in practical deployments.","PeriodicalId":275067,"journal":{"name":"Proceedings of the 2023 10th International Conference on Wireless Communication and Sensor Networks","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131178437","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zhi Li, Di Liu, Xiao Liao, Shi Feng, Xueying Ding, Wei Cui
Based on edge computing, wireless communication, and other technologies, the power distribution Internet of Things with edge IoT agent as the core, will realize comprehensive perception, data fusion, and intelligent application of power distribution network, and effectively promote the rapid development of the power grid. However, the power usage efficiency (PUE) of the edge IoT agent is the bottleneck in achieving the distribution network's sustainable computing. The edge IoT agent of power distribution Internet of Things network faces the problem of green sustainability. This paper focuses on the computing resource allocation of edge IoT agents in power distribution IoT, designs an energy-efficient green task offloading framework, and proposes an efficient dynamic task offloading strategy. The numerical results show that the task offloading strategy proposed in this paper can ensure the reasonable allocation of power distribution IoT business resources while reducing energy consumption.
{"title":"A Dynamic Task Offloading Strategy for Power Distribution IoT based on Energy Consumption","authors":"Zhi Li, Di Liu, Xiao Liao, Shi Feng, Xueying Ding, Wei Cui","doi":"10.1145/3585967.3585973","DOIUrl":"https://doi.org/10.1145/3585967.3585973","url":null,"abstract":"Based on edge computing, wireless communication, and other technologies, the power distribution Internet of Things with edge IoT agent as the core, will realize comprehensive perception, data fusion, and intelligent application of power distribution network, and effectively promote the rapid development of the power grid. However, the power usage efficiency (PUE) of the edge IoT agent is the bottleneck in achieving the distribution network's sustainable computing. The edge IoT agent of power distribution Internet of Things network faces the problem of green sustainability. This paper focuses on the computing resource allocation of edge IoT agents in power distribution IoT, designs an energy-efficient green task offloading framework, and proposes an efficient dynamic task offloading strategy. The numerical results show that the task offloading strategy proposed in this paper can ensure the reasonable allocation of power distribution IoT business resources while reducing energy consumption.","PeriodicalId":275067,"journal":{"name":"Proceedings of the 2023 10th International Conference on Wireless Communication and Sensor Networks","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130607707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The Internet's sharing and openness have made information interaction more vulnerable to security risks. As a result, a comprehensive evaluation of the security of computer network systems has become a more effective means of preventing various network security problems. In recent years, there have been many network security evaluation methods proposed to address this issue, but not all of them are effective. Therefore, this paper analyzes existing network security evaluation methods and proposes a new model based on BP neural network and AHP jointly. The proposed model combines the advantages of BP neural network and hierarchical analysis (AHP) to provide a comprehensive and accurate evaluation of network security. The BP neural network is used to evaluate the risk level of each security factor, while AHP is used to calculate the weights of each security factor. The weights reflect the relative importance of each factor in determining the overall security level of the network. To verify the applicability of the proposed model, empirical research is conducted. The results demonstrate that the model can effectively evaluate network security comprehensively. The model's accuracy and effectiveness make it a promising approach to evaluate the security of computer network systems. Additionally, it can help in developing strategies to enhance network security by identifying potential vulnerabilities and assessing the effectiveness of security measures implemented. In conclusion, the model provides a useful tool for organizations to manage network security effectively.
{"title":"Research on Network Security Evaluation Model Based on AHP and BP Neural Network","authors":"Jingfeng Zhu","doi":"10.1145/3585967.3585987","DOIUrl":"https://doi.org/10.1145/3585967.3585987","url":null,"abstract":"The Internet's sharing and openness have made information interaction more vulnerable to security risks. As a result, a comprehensive evaluation of the security of computer network systems has become a more effective means of preventing various network security problems. In recent years, there have been many network security evaluation methods proposed to address this issue, but not all of them are effective. Therefore, this paper analyzes existing network security evaluation methods and proposes a new model based on BP neural network and AHP jointly. The proposed model combines the advantages of BP neural network and hierarchical analysis (AHP) to provide a comprehensive and accurate evaluation of network security. The BP neural network is used to evaluate the risk level of each security factor, while AHP is used to calculate the weights of each security factor. The weights reflect the relative importance of each factor in determining the overall security level of the network. To verify the applicability of the proposed model, empirical research is conducted. The results demonstrate that the model can effectively evaluate network security comprehensively. The model's accuracy and effectiveness make it a promising approach to evaluate the security of computer network systems. Additionally, it can help in developing strategies to enhance network security by identifying potential vulnerabilities and assessing the effectiveness of security measures implemented. In conclusion, the model provides a useful tool for organizations to manage network security effectively.","PeriodicalId":275067,"journal":{"name":"Proceedings of the 2023 10th International Conference on Wireless Communication and Sensor Networks","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129815072","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The accuracy of the multi-object tracking (MOT) based on the 2D camera without depth info is usually poor. In this paper, we propose a MOT method based on sensors composed of the camera and the ultra-wide band (UWB) radar, which are similar to the depth camera (RGB-D camera). First, we establish a backbone network to extract feature maps from video frames captured by a camera. Then, we combine Faster R-CNN with a re-ID branch to detect objects including the category, coordinate and ID. To track objects, we construct a similarity matrix to calculate the data association between the objects and their historical trajectories. The matrix's elements are calculated by the intersection over union (IoU) between the objects and their related two types of trajectories, which are based on the image data and the UWB localization data separately. Finally, the trajectories are updated by the two types of trajectories, and the recognition network is updated by the localization loss. The experimental results show that our method achieves multi-object recognition and tracking, and outperforms previous methods by a large margin on several public datasets.
{"title":"Multi-Object Tracking based on RGB-D Sensors","authors":"Keliang Zhu, Xuemei Shi, Tianzhong Zhang, Huasong Song, Jinlin Xu, Liangfeng Chen","doi":"10.1145/3585967.3585990","DOIUrl":"https://doi.org/10.1145/3585967.3585990","url":null,"abstract":"The accuracy of the multi-object tracking (MOT) based on the 2D camera without depth info is usually poor. In this paper, we propose a MOT method based on sensors composed of the camera and the ultra-wide band (UWB) radar, which are similar to the depth camera (RGB-D camera). First, we establish a backbone network to extract feature maps from video frames captured by a camera. Then, we combine Faster R-CNN with a re-ID branch to detect objects including the category, coordinate and ID. To track objects, we construct a similarity matrix to calculate the data association between the objects and their historical trajectories. The matrix's elements are calculated by the intersection over union (IoU) between the objects and their related two types of trajectories, which are based on the image data and the UWB localization data separately. Finally, the trajectories are updated by the two types of trajectories, and the recognition network is updated by the localization loss. The experimental results show that our method achieves multi-object recognition and tracking, and outperforms previous methods by a large margin on several public datasets.","PeriodicalId":275067,"journal":{"name":"Proceedings of the 2023 10th International Conference on Wireless Communication and Sensor Networks","volume":"49 12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124837797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the proposed algorithm, the inertial navigation and the improved weighted centroid position calculation method work independently in a loose combination manner, and achieve the optimal estimation of integrated positioning by fusing the sensor information from different sources, realizing the design goal of wireless sensor network to provide absolute position information for the inertial navigation system. The experimental results show that the improved weighted centroid positioning/inertial navigation method in the network environment is better than the improved weighted centroid positioning or inertial navigation method in terms of positioning accuracy and noise, reflecting the complementary advantages of absolute positioning and relative positioning and the ability to provide high-precision coordinates in the static working environment. In theory, the CENTER OF GRAVITY (COG) algorithm uses the trilateral measurement method to realize the location of another node on the premise that the received signal strength of the three anchor nodes in the wireless sensor network is known. However, due to the uncertain component of the received signal strength of the anchor node, the location of another node cannot be completely determined in actual operation, so this paper uses some additional algorithms to ensure the feasibility of node location, such as the least squares algorithm [1] and the maximum likelihood estimation method [2].In order to control the cost, a few location-aware nodes, called anchor nodes, are deployed in the wireless sensor network environment. Mobile nodes in the network estimate their position through these anchor nodes. Therefore, this paper proposes a modified form of COG algorithm, ICOG(Improved CENTER OF GRAVITY ). The proposed algorithm adopts an anchor node position verification mechanism by observing the consistency of the received signal strength quality. The anchor nodes near the mobile node use the received signal strength to seek to verify the actual position or proximity of other anchor nodes near it. This process alleviates the multipath effect in the process of radio wave transmission, especially in the closed environment, thus effectively controlling the positioning error and uncertainty.
在本文提出的算法中，惯性导航和改进的加权质心位置计算方法以松散组合的方式独立工作，通过融合不同来源的传感器信息来实现集成定位的最优估计，实现了无线传感器网络为惯性导航系统提供绝对位置信息的设计目标。实验结果表明，网络环境下改进的加权质心定位/惯导方法在定位精度和噪声方面都优于改进的加权质心定位或惯导方法，体现了绝对定位和相对定位的互补优势，能够在静态工作环境下提供高精度坐标。理论上，重心(CENTER OF GRAVITY, COG)算法在无线传感器网络中三个锚节点的接收信号强度已知的前提下，采用三边测量方法来实现另一个节点的位置。然而，由于锚节点接收信号强度的不确定性成分，在实际操作中无法完全确定其他节点的位置，因此本文采用了一些额外的算法来保证节点位置的可行性，如最小二乘算法[1]和最大似然估计方法[2]。为了控制成本，在无线传感器网络环境中部署了几个位置感知节点，称为锚节点。网络中的移动节点通过这些锚节点来估计自己的位置。为此，本文提出了一种改进的COG算法ICOG(Improved CENTER of GRAVITY)。该算法通过观察接收信号强度质量的一致性，采用锚节点位置验证机制。移动节点附近的锚节点使用接收到的信号强度来寻求验证其附近其他锚节点的实际位置或距离。该过程缓解了无线电波传输过程中的多径效应，特别是在封闭环境下，从而有效地控制了定位误差和不确定性。
{"title":"Establishment of a new improved weighted centroid position solution method in network environment","authors":"Shiwei Li","doi":"10.1145/3585967.3585971","DOIUrl":"https://doi.org/10.1145/3585967.3585971","url":null,"abstract":"In the proposed algorithm, the inertial navigation and the improved weighted centroid position calculation method work independently in a loose combination manner, and achieve the optimal estimation of integrated positioning by fusing the sensor information from different sources, realizing the design goal of wireless sensor network to provide absolute position information for the inertial navigation system. The experimental results show that the improved weighted centroid positioning/inertial navigation method in the network environment is better than the improved weighted centroid positioning or inertial navigation method in terms of positioning accuracy and noise, reflecting the complementary advantages of absolute positioning and relative positioning and the ability to provide high-precision coordinates in the static working environment. In theory, the CENTER OF GRAVITY (COG) algorithm uses the trilateral measurement method to realize the location of another node on the premise that the received signal strength of the three anchor nodes in the wireless sensor network is known. However, due to the uncertain component of the received signal strength of the anchor node, the location of another node cannot be completely determined in actual operation, so this paper uses some additional algorithms to ensure the feasibility of node location, such as the least squares algorithm [1] and the maximum likelihood estimation method [2].In order to control the cost, a few location-aware nodes, called anchor nodes, are deployed in the wireless sensor network environment. Mobile nodes in the network estimate their position through these anchor nodes. Therefore, this paper proposes a modified form of COG algorithm, ICOG(Improved CENTER OF GRAVITY ). The proposed algorithm adopts an anchor node position verification mechanism by observing the consistency of the received signal strength quality. The anchor nodes near the mobile node use the received signal strength to seek to verify the actual position or proximity of other anchor nodes near it. This process alleviates the multipath effect in the process of radio wave transmission, especially in the closed environment, thus effectively controlling the positioning error and uncertainty.","PeriodicalId":275067,"journal":{"name":"Proceedings of the 2023 10th International Conference on Wireless Communication and Sensor Networks","volume":"141-142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117221425","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the increasing complexity of the environment in high-speed railway stations and the growing demand for in-station navigation and location services, it is critical to investigate an accurate and dependable intelligent guidance system for cars in the in-station network. This paper intends to use GNSS indoor satellite base station positioning system and an indoor navigation path planning method based on improved A* algorithm to realize mutual intelligent guidance between passengers in the station and the network car by analyzing the technical status and existing problems of indoor positioning and path planning, combined with the actual situation in high-speed railway station. To begin, the indoor satellite positioning system is deployed, and satellite analog signals are broadcast to provide positioning services for general navigation and positioning terminals, resulting in accurate station positioning. The search efficiency of the A* algorithm is then improved by optimizing the search strategy and heuristic function of the traditional A* algorithm. The path length is reduced by optimizing redundant nodes. The actual verification shows that the improved A* algorithm has a 5% shorter path length than the traditional A* algorithm. When compared to the traditional A* algorithm, the improved A* algorithm can save more than 60% of the planning time. Finally, network car driver and passenger services will be provided to guide passengers and drivers to the best possible position to board the bus quickly and intelligently.
{"title":"Research on Intelligent Guidance Method for Vehicles in High-Speed Railway Station Based on GNSS Indoor Positioning","authors":"Changhua Wang, Zhaohui Lin, Xihao Zhu, Yuhai Zheng, Hancheng Yu","doi":"10.1145/3585967.3585979","DOIUrl":"https://doi.org/10.1145/3585967.3585979","url":null,"abstract":"With the increasing complexity of the environment in high-speed railway stations and the growing demand for in-station navigation and location services, it is critical to investigate an accurate and dependable intelligent guidance system for cars in the in-station network. This paper intends to use GNSS indoor satellite base station positioning system and an indoor navigation path planning method based on improved A* algorithm to realize mutual intelligent guidance between passengers in the station and the network car by analyzing the technical status and existing problems of indoor positioning and path planning, combined with the actual situation in high-speed railway station. To begin, the indoor satellite positioning system is deployed, and satellite analog signals are broadcast to provide positioning services for general navigation and positioning terminals, resulting in accurate station positioning. The search efficiency of the A* algorithm is then improved by optimizing the search strategy and heuristic function of the traditional A* algorithm. The path length is reduced by optimizing redundant nodes. The actual verification shows that the improved A* algorithm has a 5% shorter path length than the traditional A* algorithm. When compared to the traditional A* algorithm, the improved A* algorithm can save more than 60% of the planning time. Finally, network car driver and passenger services will be provided to guide passengers and drivers to the best possible position to board the bus quickly and intelligently.","PeriodicalId":275067,"journal":{"name":"Proceedings of the 2023 10th International Conference on Wireless Communication and Sensor Networks","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116549218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：