To cope with the unprecedented surge in demand for data computing, the promising unmanned aerial vehicle (UAV) assisted mobile edge computing (MEC) has been proposed to enable the network edges to provide closer data processing for users. Hence, data offloading from user to the MEC server will require more efficient. The integration of nonorthogonal multiple access (NOMA) technique with MEC has been shown to provide applications with lower latency and higher energy efficiency. To further enhance offloading performance, in this work, we propose an offloading scheme based on the data division and fusion reinforcement learning (DF-RL) algorithm to handle tasks through multi-user and multi-UAV collaboration. We formulate the optimization problem to minimize the delay and energy consumption of the system, and optimize the offloading strategy through the DF-RL algorithm. Firstly, the data fusion module is used to reduce the processing of repetitive tasks. Secondly, the task is divided into sub-tasks by task segmentation module to better complete the cooperation between UAVs. Finally, reinforcement learning (RL) is used to solve the problem and the optimal offloading strategy decision is obtained. Simulation results show that our algorithm not only has great superiority, but also improves the successful rate of the tasks.
{"title":"Collaborative Computation Offloading in Multi-UAV-MEC Networks: A Reinforcement Learning Approach","authors":"Yaoping Zeng, Ting Yang, Yanwei Hu","doi":"10.1145/3573942.3573988","DOIUrl":"https://doi.org/10.1145/3573942.3573988","url":null,"abstract":"To cope with the unprecedented surge in demand for data computing, the promising unmanned aerial vehicle (UAV) assisted mobile edge computing (MEC) has been proposed to enable the network edges to provide closer data processing for users. Hence, data offloading from user to the MEC server will require more efficient. The integration of nonorthogonal multiple access (NOMA) technique with MEC has been shown to provide applications with lower latency and higher energy efficiency. To further enhance offloading performance, in this work, we propose an offloading scheme based on the data division and fusion reinforcement learning (DF-RL) algorithm to handle tasks through multi-user and multi-UAV collaboration. We formulate the optimization problem to minimize the delay and energy consumption of the system, and optimize the offloading strategy through the DF-RL algorithm. Firstly, the data fusion module is used to reduce the processing of repetitive tasks. Secondly, the task is divided into sub-tasks by task segmentation module to better complete the cooperation between UAVs. Finally, reinforcement learning (RL) is used to solve the problem and the optimal offloading strategy decision is obtained. Simulation results show that our algorithm not only has great superiority, but also improves the successful rate of the tasks.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133693751","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}
Aiming at the problems of image encryption, such as poor encryption effect and poor security, a compound chaotic map ILSC is designed with Logistic map and Sine map as seed maps. Based on this, an image encryption algorithm based on compound chaotic system and dynamic DNA coding is proposed. First, according to the DNA random coding rules, the plaintext image is converted into a DNA matrix, and the scrambling operation is performed on it, and then the rows and columns of the DNA matrix are XORed to obtain the ciphertext image. Theoretical analysis and simulation results show that the proposed algorithm has a larger key space, the ciphertext image has higher information entropy, and can effectively resist statistical attacks, brute force attacks and other attack methods, and has better performance.
{"title":"Image Encryption Algorithm Based on Compound Chaotic System and DNA Coding","authors":"Si-Peng Cheng, Xiaodong Zhang, Wen Jiang","doi":"10.1145/3573942.3574060","DOIUrl":"https://doi.org/10.1145/3573942.3574060","url":null,"abstract":"Aiming at the problems of image encryption, such as poor encryption effect and poor security, a compound chaotic map ILSC is designed with Logistic map and Sine map as seed maps. Based on this, an image encryption algorithm based on compound chaotic system and dynamic DNA coding is proposed. First, according to the DNA random coding rules, the plaintext image is converted into a DNA matrix, and the scrambling operation is performed on it, and then the rows and columns of the DNA matrix are XORed to obtain the ciphertext image. Theoretical analysis and simulation results show that the proposed algorithm has a larger key space, the ciphertext image has higher information entropy, and can effectively resist statistical attacks, brute force attacks and other attack methods, and has better performance.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131396084","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}
Rogeany Kanza, Chenyu Huang, Allah Rakhio Junejo, Zhuoming Li
The exponential evolution of big data with its increasing volumes, especially when it comes to videos from smart devices and video sites, has become a real challenge to video analysis tasks algorithms. Processing and storage difficulties are the main problems for these traditional video processing architectures that mostly use RGB frames for video analysis tasks. The process of decoding compressed videos is time-consuming and requires a lot of storage space. Although existing convolutional neural networks (CNNs) based video analysis architectures have realized notable advancements, they still hardly meet the requirements of many real-time scenarios and real-world applications. This is one of the motivations for the computer vision community to move to action recognition with compressed domain compressed videos in order to overcome the aforementioned issues. On the other hand, the performance of prominent methods is very dependent on the correct setting of initialization parameters. The choice of initialization has an impact on the final generalization performance of a neural network. This work proposes a weight initialization technique in compressed domain for compressed videos action recognition tasks. Our approach was tested on UFC-101 and HDBM-51 datasets. The performance evaluation shows the effectiveness of our proposed methodology.
{"title":"A Weight Initialization Method for Compressed Video Action Recognition in Compressed Domain","authors":"Rogeany Kanza, Chenyu Huang, Allah Rakhio Junejo, Zhuoming Li","doi":"10.1145/3573942.3574089","DOIUrl":"https://doi.org/10.1145/3573942.3574089","url":null,"abstract":"The exponential evolution of big data with its increasing volumes, especially when it comes to videos from smart devices and video sites, has become a real challenge to video analysis tasks algorithms. Processing and storage difficulties are the main problems for these traditional video processing architectures that mostly use RGB frames for video analysis tasks. The process of decoding compressed videos is time-consuming and requires a lot of storage space. Although existing convolutional neural networks (CNNs) based video analysis architectures have realized notable advancements, they still hardly meet the requirements of many real-time scenarios and real-world applications. This is one of the motivations for the computer vision community to move to action recognition with compressed domain compressed videos in order to overcome the aforementioned issues. On the other hand, the performance of prominent methods is very dependent on the correct setting of initialization parameters. The choice of initialization has an impact on the final generalization performance of a neural network. This work proposes a weight initialization technique in compressed domain for compressed videos action recognition tasks. Our approach was tested on UFC-101 and HDBM-51 datasets. The performance evaluation shows the effectiveness of our proposed methodology.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134401425","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}
Due to the limitations of the acquisition equipment, sensors, and the illumination or reflection characteristics of the ground, the acquired point clouds will inevitably be noisy. Noise degrades the quality of point clouds and hinders the subsequent point cloud processing tasks, so the denoising technique becomes a crucial step in point cloud processing. This paper proposes a point cloud denoising algorithm based on a hybrid attention mechanism, which takes into account the complexity of the internal features of point clouds and the randomness of point cloud transformations. Generates channel and spatial attention by parallel maximum pooling and average pooling of point cloud data, trains adaptive attention weights using a multilayer perceptron with shared weights, and serially fuses them, multiplies them with the input features to obtain more robust point cloud features, and connect to the score estimation module using the residuals. By studying and analyzing the mechanism proposed in this paper, it is experimentally demonstrated that the performance of the proposed model under various noise models is vastly improved over the baseline network and outperforms the advanced denoising methods without significantly increasing the network operation cost.
{"title":"3D Point Cloud Denoising Based on Hybrid Attention Mechanism and Score Matching","authors":"Ziwei Wang, Wei Sun, Linyang Tian","doi":"10.1145/3573942.3574093","DOIUrl":"https://doi.org/10.1145/3573942.3574093","url":null,"abstract":"Due to the limitations of the acquisition equipment, sensors, and the illumination or reflection characteristics of the ground, the acquired point clouds will inevitably be noisy. Noise degrades the quality of point clouds and hinders the subsequent point cloud processing tasks, so the denoising technique becomes a crucial step in point cloud processing. This paper proposes a point cloud denoising algorithm based on a hybrid attention mechanism, which takes into account the complexity of the internal features of point clouds and the randomness of point cloud transformations. Generates channel and spatial attention by parallel maximum pooling and average pooling of point cloud data, trains adaptive attention weights using a multilayer perceptron with shared weights, and serially fuses them, multiplies them with the input features to obtain more robust point cloud features, and connect to the score estimation module using the residuals. By studying and analyzing the mechanism proposed in this paper, it is experimentally demonstrated that the performance of the proposed model under various noise models is vastly improved over the baseline network and outperforms the advanced denoising methods without significantly increasing the network operation cost.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132266286","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}
Surface defect detection is an essential procedure during industrial production. It is a challenge to establish an effective model for the surface defects inspection of products. Because defect samples are few and varied. Current supervised learning methods for object detection require large amounts of defect data, which is difficult to collect in the industrial scene. The unsupervised method based on image reconstruction often reconstructs defects. In this paper, we propose a novel surface defect detection method by fused supervised and unsupervised approaches to accurately inspect various surface defects. For unsupervised module, it employs a convolutional autoencoder (CAE) to reconstruct the defect-free image. For the supervised module, use CAE to inspect the defective area for the defective images. A novel loss function is proposed to detect defects by making the residual image between the output image of CAE and the artificial defect im to close to the defect label image. So, by adding a semantic label with all zero values to the defect-free image, the residual image of different tasks is jointly close to their respective semantic labels. Therefore, a unified loss function is used to unify the unsupervised and supervised methods. The experimental results show that the proposed method achieves better inspection accuracy.
{"title":"An Incremental Surface Defect Detection Method by Fused Unsupervised and Supervised Methods","authors":"Wanyu Deng, Wei Wang, Jiahao Jie, Dunhai Wu","doi":"10.1145/3573942.3574107","DOIUrl":"https://doi.org/10.1145/3573942.3574107","url":null,"abstract":"Surface defect detection is an essential procedure during industrial production. It is a challenge to establish an effective model for the surface defects inspection of products. Because defect samples are few and varied. Current supervised learning methods for object detection require large amounts of defect data, which is difficult to collect in the industrial scene. The unsupervised method based on image reconstruction often reconstructs defects. In this paper, we propose a novel surface defect detection method by fused supervised and unsupervised approaches to accurately inspect various surface defects. For unsupervised module, it employs a convolutional autoencoder (CAE) to reconstruct the defect-free image. For the supervised module, use CAE to inspect the defective area for the defective images. A novel loss function is proposed to detect defects by making the residual image between the output image of CAE and the artificial defect im to close to the defect label image. So, by adding a semantic label with all zero values to the defect-free image, the residual image of different tasks is jointly close to their respective semantic labels. Therefore, a unified loss function is used to unify the unsupervised and supervised methods. The experimental results show that the proposed method achieves better inspection accuracy.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116282079","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 great changes in the international situation today, whether it is the war in Afghanistan or the war between Russia and Ukraine, all of them reflect the importance of military strength to a country, and the research of precision guided weapons is a key part of improving military strength. With the rapid development of science and technology, as the core component of guided weapons, the miniaturized flight control computer system should keep pace with the times and have better performance and better reliability. In this paper, a flight control computer with high performance and strong versatility is designed based on the flight test of a certain type of missile. The flight control computer based on FPGA and DSP introduced in this paper makes full use of the respective advantages of the two processors, and has the characteristics of strong real- time processing capability, small size, light weight and low power. The computer realize the function of serial communication, discrete input and output, analog input and output, double-ended RAM storage, etc. After many flight tests, it has been shown that the system has good reliability and stability, and has certain engineering application value.
{"title":"Design and Implementation of Miniaturized Flight Control Computer Based on FPGA+DSP","authors":"Xiaofeng Yang, Chaochao Qiu","doi":"10.1145/3573942.3574004","DOIUrl":"https://doi.org/10.1145/3573942.3574004","url":null,"abstract":"With the great changes in the international situation today, whether it is the war in Afghanistan or the war between Russia and Ukraine, all of them reflect the importance of military strength to a country, and the research of precision guided weapons is a key part of improving military strength. With the rapid development of science and technology, as the core component of guided weapons, the miniaturized flight control computer system should keep pace with the times and have better performance and better reliability. In this paper, a flight control computer with high performance and strong versatility is designed based on the flight test of a certain type of missile. The flight control computer based on FPGA and DSP introduced in this paper makes full use of the respective advantages of the two processors, and has the characteristics of strong real- time processing capability, small size, light weight and low power. The computer realize the function of serial communication, discrete input and output, analog input and output, double-ended RAM storage, etc. After many flight tests, it has been shown that the system has good reliability and stability, and has certain engineering application value.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122952727","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 embedding capacity of the traditional reversible information hiding algorithm based on the asymmetric prediction error histogram is limited by the number of pixels at the peak point, the available pixels in the image are not fully utilized, resulting in the increase of invalid shift points, which makes the visual quality of camouflage image poor. In this paper, a new multi-bit translation reversible information hiding algorithm based on asymmetric prediction error histogram is proposed, which aims to greatly improve the embedding capacity of carrier image with minimal impact on image quality. The algorithm makes more use of the correlation between adjacent pixels, so that the error value of pixels is more concentrated near the peak point, and the difference between the peak point and the zero point is reduced, so as to obtain a more concentrated asymmetric prediction error histogram, which makes the embedding capacity larger. Meanwhile, the algorithm is not limited to the pixels of the peak point, and the error pixels that meet the conditions around the peak point are also embedded with secret information. The experimental results show that the algorithm can effectively reduce the invalid shifted pixels and reduce the distortion of the camouflage image while maintaining the large embedding capacity.
{"title":"High capacity reversible information hiding algorithm based on asymmetric prediction error histogram","authors":"Fang Ren, Wei Hou, Mingyu Yu, Cong Tian","doi":"10.1145/3573942.3574067","DOIUrl":"https://doi.org/10.1145/3573942.3574067","url":null,"abstract":"The embedding capacity of the traditional reversible information hiding algorithm based on the asymmetric prediction error histogram is limited by the number of pixels at the peak point, the available pixels in the image are not fully utilized, resulting in the increase of invalid shift points, which makes the visual quality of camouflage image poor. In this paper, a new multi-bit translation reversible information hiding algorithm based on asymmetric prediction error histogram is proposed, which aims to greatly improve the embedding capacity of carrier image with minimal impact on image quality. The algorithm makes more use of the correlation between adjacent pixels, so that the error value of pixels is more concentrated near the peak point, and the difference between the peak point and the zero point is reduced, so as to obtain a more concentrated asymmetric prediction error histogram, which makes the embedding capacity larger. Meanwhile, the algorithm is not limited to the pixels of the peak point, and the error pixels that meet the conditions around the peak point are also embedded with secret information. The experimental results show that the algorithm can effectively reduce the invalid shifted pixels and reduce the distortion of the camouflage image while maintaining the large embedding capacity.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117098277","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 traditional channel estimation methods for Filter Bank Multicarrier (FBMC) systems have some drawbacks, such as unreasonable pilot structure settings and poor estimation accuracy. Because FBMC/OQAM systems have inherent imaginary interference, this paper presents two new block pilots based on the traditional channel estimation methods. First, the system is briefly introduced. Because the traditional two-column pairs of pilot method (POP) has poor estimation accuracy and anti-noise performance, the structure of the pilot is reset to reduce noise interference and improve the estimation performance from the basic reason. Then aiming at the interference approximation method (IAM), because of the characteristics of its three-column pilot settings, the equivalent power of the pilot is high, which results in the excessive amplitude of the time-domain pilot signal and the pressure on the RF power amplifier. Therefore, the structure of IAM is modified to effectively suppress the amplitude. The simulation results show that the algorithm presented in this paper has a good bit error rate (BER) performance and small mean square error (MSE).
{"title":"Improvement of Channel Estimation Method Based on Preamble Pilot in FBMC System","authors":"Leu-Chin Chen, Xihai Xie","doi":"10.1145/3573942.3573995","DOIUrl":"https://doi.org/10.1145/3573942.3573995","url":null,"abstract":"The traditional channel estimation methods for Filter Bank Multicarrier (FBMC) systems have some drawbacks, such as unreasonable pilot structure settings and poor estimation accuracy. Because FBMC/OQAM systems have inherent imaginary interference, this paper presents two new block pilots based on the traditional channel estimation methods. First, the system is briefly introduced. Because the traditional two-column pairs of pilot method (POP) has poor estimation accuracy and anti-noise performance, the structure of the pilot is reset to reduce noise interference and improve the estimation performance from the basic reason. Then aiming at the interference approximation method (IAM), because of the characteristics of its three-column pilot settings, the equivalent power of the pilot is high, which results in the excessive amplitude of the time-domain pilot signal and the pressure on the RF power amplifier. Therefore, the structure of IAM is modified to effectively suppress the amplitude. The simulation results show that the algorithm presented in this paper has a good bit error rate (BER) performance and small mean square error (MSE).","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"138 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121754190","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 problem of ship trajectory association is well recognized in the overlapping area cross multiple sensors. In this paper, an improved method based on weighted cascade Hausdorff distance, with a variable time sliding window, is proposed. This method can effectively solve the problem of ship target fusion in the field of border and coastal defense, thereby providing a basis for the next step of ship monitoring and management. The similarities of tracks from different radars are determined by the proposed method, which combines the information of both ship position and motion characteristics. Several experiments are designed, with both real and simulated track data as input, to evaluate the effectiveness of the proposed method. The results showed that the method, due to the configurable parameters of time sliding window, has good universality to meet the needs of different radar frequency. The best performance among different configuration settings has the better advantage of 10%-20% improvement compared with the traditional Hausdorff distance model with fixed time window.
{"title":"Using More Information to Determine Trajectory Association: An Improved Method Based on Weighted Cascade Hausdorff Distance","authors":"Y. Guo, Han Jiao","doi":"10.1145/3573942.3574012","DOIUrl":"https://doi.org/10.1145/3573942.3574012","url":null,"abstract":"The problem of ship trajectory association is well recognized in the overlapping area cross multiple sensors. In this paper, an improved method based on weighted cascade Hausdorff distance, with a variable time sliding window, is proposed. This method can effectively solve the problem of ship target fusion in the field of border and coastal defense, thereby providing a basis for the next step of ship monitoring and management. The similarities of tracks from different radars are determined by the proposed method, which combines the information of both ship position and motion characteristics. Several experiments are designed, with both real and simulated track data as input, to evaluate the effectiveness of the proposed method. The results showed that the method, due to the configurable parameters of time sliding window, has good universality to meet the needs of different radar frequency. The best performance among different configuration settings has the better advantage of 10%-20% improvement compared with the traditional Hausdorff distance model with fixed time window.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127606369","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}
At low SNRs, the analog signal will be swamped by noise. Aiming at the low estimation accuracy of the traditional signal bandwidth estimation algorithms, a signal bandwidth estimation method based on the Wavelet reconstruction is proposed in this paper. Firstly, the influence of noise is reduced by means of data segmentation cross-correlation. Secondly, the envelope of signal amplitude spectrum is extracted by the wavelet low-frequency reconstruction. Finally, according to its envelope, the boundary can be found of signal amplitude spectrum by the difference operation. The estimation is completed of the signal zero-crossing bandwidth. In this method, the wavelet reconstruction is applied to signal bandwidth estimation for the first time, which can reduce the negative impact of signal randomness on the spectrum envelop. In addition, the extreme point searching algorithm is designed to confirm the upper and lower frequency bands of the reconstructed spectrum envelope, which is easy to implement and can be directly applied in the engineering field. The experimental results show that the proposed method is robust and can achieve good results at low SNRs.
{"title":"Signal Bandwidth Estimation Based on the Wavelet Reconstruction","authors":"Tian-Fang Ma, Wenxiu Zheng, Wanshun Xiu","doi":"10.1145/3573942.3574116","DOIUrl":"https://doi.org/10.1145/3573942.3574116","url":null,"abstract":"At low SNRs, the analog signal will be swamped by noise. Aiming at the low estimation accuracy of the traditional signal bandwidth estimation algorithms, a signal bandwidth estimation method based on the Wavelet reconstruction is proposed in this paper. Firstly, the influence of noise is reduced by means of data segmentation cross-correlation. Secondly, the envelope of signal amplitude spectrum is extracted by the wavelet low-frequency reconstruction. Finally, according to its envelope, the boundary can be found of signal amplitude spectrum by the difference operation. The estimation is completed of the signal zero-crossing bandwidth. In this method, the wavelet reconstruction is applied to signal bandwidth estimation for the first time, which can reduce the negative impact of signal randomness on the spectrum envelop. In addition, the extreme point searching algorithm is designed to confirm the upper and lower frequency bands of the reconstructed spectrum envelope, which is easy to implement and can be directly applied in the engineering field. The experimental results show that the proposed method is robust and can achieve good results at low SNRs.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126751516","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：