Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065619
Mengxin Zhang, Xiaofeng Qiu
Deep neural networks (DNNs) are playing an increasingly significant role in the modern world. However, they are weak to adversarial samples that are generated by adding specially crafted perturbations. Most defenses against adversarial samples focused on refining the DNN models, which often sacrifice the performance and computational cost of models on benign samples. In this paper, we propose a manifold distance detection method to distinguish legitimate samples and adversarial samples by measuring the different distances on the manifold. The manifold distance detection method neither modifies the protected models nor requires knowledge of the process for generating adversarial samples. Inspired by the effectiveness of the manifold distance detection, we demonstrated a well-designed orchestrated defense strategy, named Manifold Distance Judge (MDJ), which selects the best image processing method that will effectively expand the manifold distance between legitimate and adversarial samples, and thus, enhances the performance of the following manifold distance detection method. Tests on the ImageNet dataset, the MDJ is effective against the most adversarial samples under white-box, gray-box, and black-box attack scenarios. We show empirically that the orchestration strategy MDJ is significantly better than Feature Squeezing on the recall rate. Meanwhile, MDJ achieves high detection rates against CW attack and DI-FGSM attack.
{"title":"Adversarial Samples Defense Strategy Based on Service Orchestration","authors":"Mengxin Zhang, Xiaofeng Qiu","doi":"10.1109/ICCC56324.2022.10065619","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065619","url":null,"abstract":"Deep neural networks (DNNs) are playing an increasingly significant role in the modern world. However, they are weak to adversarial samples that are generated by adding specially crafted perturbations. Most defenses against adversarial samples focused on refining the DNN models, which often sacrifice the performance and computational cost of models on benign samples. In this paper, we propose a manifold distance detection method to distinguish legitimate samples and adversarial samples by measuring the different distances on the manifold. The manifold distance detection method neither modifies the protected models nor requires knowledge of the process for generating adversarial samples. Inspired by the effectiveness of the manifold distance detection, we demonstrated a well-designed orchestrated defense strategy, named Manifold Distance Judge (MDJ), which selects the best image processing method that will effectively expand the manifold distance between legitimate and adversarial samples, and thus, enhances the performance of the following manifold distance detection method. Tests on the ImageNet dataset, the MDJ is effective against the most adversarial samples under white-box, gray-box, and black-box attack scenarios. We show empirically that the orchestration strategy MDJ is significantly better than Feature Squeezing on the recall rate. Meanwhile, MDJ achieves high detection rates against CW attack and DI-FGSM attack.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122382713","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}
Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065937
Jianing Li, Yuan Jiang, Lei Zhao, Bin Wang
Hybrid precoding has evolved into an essential technology in millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) systems due to the low demand for the number of radio frequency (RF) chains. In this paper, in order to reduce the computational complexity of hybrid precoding, we propose a low-complexity two-stage multiuser hybrid precoding scheme. In the first stage, we focus on how to reduce the computational complexity under the premise of acceptable sum spectral efficiency loss. In the second stage, block diagonalization (BD) method is adopted to design digital precoder and classical water-filling method is utilized to address power allocation problem. Simulation results reveal that the proposed precoding scheme can achieve satisfactory level from the viewpoint of computational complexity, and meanwhile spectral efficiency can be guaranteed.
{"title":"Low-Complexity Multiuser Hybrid Precoding with Partially-Connected Architecture","authors":"Jianing Li, Yuan Jiang, Lei Zhao, Bin Wang","doi":"10.1109/ICCC56324.2022.10065937","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065937","url":null,"abstract":"Hybrid precoding has evolved into an essential technology in millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) systems due to the low demand for the number of radio frequency (RF) chains. In this paper, in order to reduce the computational complexity of hybrid precoding, we propose a low-complexity two-stage multiuser hybrid precoding scheme. In the first stage, we focus on how to reduce the computational complexity under the premise of acceptable sum spectral efficiency loss. In the second stage, block diagonalization (BD) method is adopted to design digital precoder and classical water-filling method is utilized to address power allocation problem. Simulation results reveal that the proposed precoding scheme can achieve satisfactory level from the viewpoint of computational complexity, and meanwhile spectral efficiency can be guaranteed.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"250 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122710845","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}
Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065693
Jiayun Xu, Weiting Qu, Dixin Li, Changjiang Zhang
Automatic music generation is regarded as one of the most concerning research areas. However, the current music generation AI model lacks mainstream algorithms and norms, including model evaluation standards and objective music quality measurements. In this paper, we conducted experiments on traditional statistical models, machine learning models and deep learning models to generate music, respectively involving Markov Chain, SVM, Random Forest, LSTM, GAN models and their variants. In addition, we also proposed three new quantitative methods to measure the quality of computer-generated music using technical metrics: the Key Confidence Test, the Random Walk Test and the Word2Vec Similarity Test. These methods could be used to measure the quality of generated music and avoid the subjectivity of manual evaluation, thus providing reference for future music evaluation tasks.
{"title":"The Music Generation Road from Statistical Method to Deep Learning","authors":"Jiayun Xu, Weiting Qu, Dixin Li, Changjiang Zhang","doi":"10.1109/ICCC56324.2022.10065693","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065693","url":null,"abstract":"Automatic music generation is regarded as one of the most concerning research areas. However, the current music generation AI model lacks mainstream algorithms and norms, including model evaluation standards and objective music quality measurements. In this paper, we conducted experiments on traditional statistical models, machine learning models and deep learning models to generate music, respectively involving Markov Chain, SVM, Random Forest, LSTM, GAN models and their variants. In addition, we also proposed three new quantitative methods to measure the quality of computer-generated music using technical metrics: the Key Confidence Test, the Random Walk Test and the Word2Vec Similarity Test. These methods could be used to measure the quality of generated music and avoid the subjectivity of manual evaluation, thus providing reference for future music evaluation tasks.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122780421","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}
A robot senses its surroundings through its “skin.” Through this tactile sensing method, a robot can obtain tactile data of various shapes and sharp objects. Then, a robot can analyze whether objects are sharp and dangerous through these tactile data. This study proposes a k-means algorithm-based tactile data recognition method for sharp and dangerous objects for robots. It develops a distributed pressure tactile sensing device that aims to simulate how the human skin layer works. By using this device, multiple sets of data are obtained after collecting the data of seven types of objects with different degrees of sharpness, namely, a hobby knife, sharp pliers, a diamond-shaped block, a square charger, a pencil-shaped block, a ping-pong ball, and a cylindrical block. The data are classified and stored using the k-means algorithm. By sensing the data of the seven types of sharp objects studied in this work in real time on the developed device for analysis, human brain's judgment on the sharpness of the objects is simulated. Through the analysis of a large amount of experimental data and algorithm optimization, experimental results show that the device can recognize relatively regular square objects, objects with curved surfaces with small changes in the radius of curvature, and objects with tips of less complexity. Recognition accuracy can reach 95%.
{"title":"k-Means-Based Tactile Data Recognition Method for Sharp and Dangerous Objects for Robots","authors":"Jing Yang, Shunyu Cen, Xiangyu Zhang, Honglin Luo, Taohong Zhao, Guangshu Wei, Zukun Yu, Qinglang Li","doi":"10.1109/ICCC56324.2022.10066027","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10066027","url":null,"abstract":"A robot senses its surroundings through its “skin.” Through this tactile sensing method, a robot can obtain tactile data of various shapes and sharp objects. Then, a robot can analyze whether objects are sharp and dangerous through these tactile data. This study proposes a k-means algorithm-based tactile data recognition method for sharp and dangerous objects for robots. It develops a distributed pressure tactile sensing device that aims to simulate how the human skin layer works. By using this device, multiple sets of data are obtained after collecting the data of seven types of objects with different degrees of sharpness, namely, a hobby knife, sharp pliers, a diamond-shaped block, a square charger, a pencil-shaped block, a ping-pong ball, and a cylindrical block. The data are classified and stored using the k-means algorithm. By sensing the data of the seven types of sharp objects studied in this work in real time on the developed device for analysis, human brain's judgment on the sharpness of the objects is simulated. Through the analysis of a large amount of experimental data and algorithm optimization, experimental results show that the device can recognize relatively regular square objects, objects with curved surfaces with small changes in the radius of curvature, and objects with tips of less complexity. Recognition accuracy can reach 95%.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"362 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122815340","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}
Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065808
Hang Yin, Bowen Wang, Nanxi Li, Jianchi Zhu, X. She
The development of 5G generates the promotion of mMTC scenarios such as HOT and V2X, which highlights the requirements of positioning enhancement. In this paper, NR positioning evolution is analyzed from 3GPP standard perspective. we provide the analysis of basic positioning method introduced in Rel-16 and summary the enhancement for improving the accuracy and reducing the latency on NR positioning in Rel-17. Moreover, in order to meet the services' requirement defined in 3GPP SA WG, we propose the potential techniques that can enhance the NR positioning for the newly introduced scenarios in Rel-18.
{"title":"Analysis of NR Positioning Evolution: From Scenarios to Techniques","authors":"Hang Yin, Bowen Wang, Nanxi Li, Jianchi Zhu, X. She","doi":"10.1109/ICCC56324.2022.10065808","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065808","url":null,"abstract":"The development of 5G generates the promotion of mMTC scenarios such as HOT and V2X, which highlights the requirements of positioning enhancement. In this paper, NR positioning evolution is analyzed from 3GPP standard perspective. we provide the analysis of basic positioning method introduced in Rel-16 and summary the enhancement for improving the accuracy and reducing the latency on NR positioning in Rel-17. Moreover, in order to meet the services' requirement defined in 3GPP SA WG, we propose the potential techniques that can enhance the NR positioning for the newly introduced scenarios in Rel-18.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122942408","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}
Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10066043
Huimin Zhang, Guangyi Liu, N. Li, Zhou Tong, Quan Zhao, Junshuai Sun
Service-based radio access network (RAN) which enables RAN to support diversified applications and vertical industries has aroused the widespread interest. The feasibility verification of the new architecture is particularly important before further research, which is the focus of this paper. This work presents the multi-state Markov approach into the service-based RAN for performance analysis. The key phases, namely orchestration and transmission phase, are extracted to build the multi-state Markov model. And the closed expression of the Markov characteristics are given. We set the simulator according to cell deployment and the task processing to validate the proposed model. Also, the evaluation results of Markov characteristics and typical performance metrics are provided which shows the accuracy of our model.
{"title":"Performance Analysis of Service-Based RAN via Multi-state Markov Chain","authors":"Huimin Zhang, Guangyi Liu, N. Li, Zhou Tong, Quan Zhao, Junshuai Sun","doi":"10.1109/ICCC56324.2022.10066043","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10066043","url":null,"abstract":"Service-based radio access network (RAN) which enables RAN to support diversified applications and vertical industries has aroused the widespread interest. The feasibility verification of the new architecture is particularly important before further research, which is the focus of this paper. This work presents the multi-state Markov approach into the service-based RAN for performance analysis. The key phases, namely orchestration and transmission phase, are extracted to build the multi-state Markov model. And the closed expression of the Markov characteristics are given. We set the simulator according to cell deployment and the task processing to validate the proposed model. Also, the evaluation results of Markov characteristics and typical performance metrics are provided which shows the accuracy of our model.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122593416","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}
Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065957
Ning Tang, Yuming Feng, B. Onasanya, Wei Zhang
This paper studies the asymptotic stability of nonlin-ear systems which is regulated by using fuzzy impulsive control. First of all, the system was formulated, the Lyapunov function was constructed, and then the fuzzy control component required for the nonlinear system to exhibit global asymptotic exponential stability under the regulation of the impulsive controller was developed. A unique fuzzy concept was introduced herein, which, compared to the conventional precise counterpart, was defined to perform only scalar approximations. Subsequently, a set of conditions sufficient for global asymptotic exponential stability was proposed for the impulsive controller. Halany inequality and its key generalizations were used while working out the mathematical proofs. Finally, examples were given to verify the general results obtained and their applicability.
{"title":"Fuzzy Alternate Control Delayed Systems","authors":"Ning Tang, Yuming Feng, B. Onasanya, Wei Zhang","doi":"10.1109/ICCC56324.2022.10065957","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065957","url":null,"abstract":"This paper studies the asymptotic stability of nonlin-ear systems which is regulated by using fuzzy impulsive control. First of all, the system was formulated, the Lyapunov function was constructed, and then the fuzzy control component required for the nonlinear system to exhibit global asymptotic exponential stability under the regulation of the impulsive controller was developed. A unique fuzzy concept was introduced herein, which, compared to the conventional precise counterpart, was defined to perform only scalar approximations. Subsequently, a set of conditions sufficient for global asymptotic exponential stability was proposed for the impulsive controller. Halany inequality and its key generalizations were used while working out the mathematical proofs. Finally, examples were given to verify the general results obtained and their applicability.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122992331","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}
Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065747
J. Liu, Lin Yuan, Zhi-Shang Feng, Xiong Chen, Zhi-Cheng Hang
With the wide application of Unmanned Aerial Vehicles (UAV), safety issues have become increasingly prominent. this paper proposes a lightweight key agreement scheme for UAV network (UAV-KAS) to solve the security problem of UAV communication, we use one-way hash for mutual identity authentication and Elliptic Curve Diffie-Hellman (ECDH) for key agreement, which improves the security of key agreement and reduces the calculation and communication cost of key agreement. The security and performance analysis show that the UAV-KAS has higher security and lower calculation cost. The proposed scheme improves the communication security problem of autonomous cooperation of UAVs. Moreover, it supports the joining and exiting of UAV, which improves the robustness of the UAVs network and can be applied to the dynamic network of UAVs with limited resources.
{"title":"A Lightweight Key Agreement Scheme for UAV Network","authors":"J. Liu, Lin Yuan, Zhi-Shang Feng, Xiong Chen, Zhi-Cheng Hang","doi":"10.1109/ICCC56324.2022.10065747","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065747","url":null,"abstract":"With the wide application of Unmanned Aerial Vehicles (UAV), safety issues have become increasingly prominent. this paper proposes a lightweight key agreement scheme for UAV network (UAV-KAS) to solve the security problem of UAV communication, we use one-way hash for mutual identity authentication and Elliptic Curve Diffie-Hellman (ECDH) for key agreement, which improves the security of key agreement and reduces the calculation and communication cost of key agreement. The security and performance analysis show that the UAV-KAS has higher security and lower calculation cost. The proposed scheme improves the communication security problem of autonomous cooperation of UAVs. Moreover, it supports the joining and exiting of UAV, which improves the robustness of the UAVs network and can be applied to the dynamic network of UAVs with limited resources.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"139 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114267186","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}
Aerial drones come in handy in a variety of science and research applications, sometimes even cause privacy harms during aerial surveillance. In many anti-drone situations, detection, tracking, and classification of drones are of great significance to secure the airspace. Drones are small in size, different in appearance, and have different flight attitudes for various flight environments, which makes the drone data sets too expensive to annotate and the foreground-background imbalance occurs in drone detection. Previous works on drone detection have focused on supervised learning, which depends on large labeled data set. To alleviate the problem of scarce labeled data sets, Semi-Supervised Learning can be employed to leverage unlabeled samples. In this paper, we propose a Semi-Supervised Object Detection method Decoupled Teacher to use unlabeled data and address the foreground-background imbalance issue. Specifically, Decoupled Teacher decouples the Exponential Moving Average mechanism in the general SSOD paradigm, and applies a fusion method of weak/strong data augmentation. We have bench-marked our method and the state-of-the-art SSOD methods using two publicly available drone data sets. The experiment results demonstrate the superior performance of our approach compared with the state-of-the-art methods.
{"title":"Decoupled Teacher for Semi-Supervised Drone Detection","authors":"Jiawei Wang, Tianyu Song, Yan Zhang, Shengmin Wang, Wenhui Lin, Zhigang Wang, Yuanyuan Qiao","doi":"10.1109/ICCC56324.2022.10065897","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065897","url":null,"abstract":"Aerial drones come in handy in a variety of science and research applications, sometimes even cause privacy harms during aerial surveillance. In many anti-drone situations, detection, tracking, and classification of drones are of great significance to secure the airspace. Drones are small in size, different in appearance, and have different flight attitudes for various flight environments, which makes the drone data sets too expensive to annotate and the foreground-background imbalance occurs in drone detection. Previous works on drone detection have focused on supervised learning, which depends on large labeled data set. To alleviate the problem of scarce labeled data sets, Semi-Supervised Learning can be employed to leverage unlabeled samples. In this paper, we propose a Semi-Supervised Object Detection method Decoupled Teacher to use unlabeled data and address the foreground-background imbalance issue. Specifically, Decoupled Teacher decouples the Exponential Moving Average mechanism in the general SSOD paradigm, and applies a fusion method of weak/strong data augmentation. We have bench-marked our method and the state-of-the-art SSOD methods using two publicly available drone data sets. The experiment results demonstrate the superior performance of our approach compared with the state-of-the-art methods.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122198378","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}
Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065827
Jianzhong Yi, Chao Dong, K. Niu, Qiulin Xue, Junping Zhang
In millimeter wave (mmWave) frequency band, the link quality is greatly affected by the environment. Coupled with the dense deployment of mmWave access points (APs) and the using of beamforming technology, beam handovers frequently occur in mobile communication systems. This paper optimizes the mmWave beam handover process using the Q-Learning method. Our proposed algorithm learns and senses the complex communication environment by the beam reporting information from the users. We consider the effects of handover cost and historical beam quality during the handover process. The adaptive handover threshold is obtained by querying the Q table according to the current state. Simulation results show that our proposed algorithm reduces the number of beam handover times and improves the system performance compared with the original scheme in the 3GPP protocol.
{"title":"Adaptive Beam Handover Algorithm Based on Reinforcement Learning for mmWave System","authors":"Jianzhong Yi, Chao Dong, K. Niu, Qiulin Xue, Junping Zhang","doi":"10.1109/ICCC56324.2022.10065827","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065827","url":null,"abstract":"In millimeter wave (mmWave) frequency band, the link quality is greatly affected by the environment. Coupled with the dense deployment of mmWave access points (APs) and the using of beamforming technology, beam handovers frequently occur in mobile communication systems. This paper optimizes the mmWave beam handover process using the Q-Learning method. Our proposed algorithm learns and senses the complex communication environment by the beam reporting information from the users. We consider the effects of handover cost and historical beam quality during the handover process. The adaptive handover threshold is obtained by querying the Q table according to the current state. Simulation results show that our proposed algorithm reduces the number of beam handover times and improves the system performance compared with the original scheme in the 3GPP protocol.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116837828","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：