Pub Date : 2021-12-01DOI: 10.1109/GCWkshps52748.2021.9682114
Anuja R. Nair, Rajesh Gupta, S. Tanwar
Demand forecasting, supply acquisition in healthcare supply chains are significant concerns spanning various organizations and bodies, rendering a crucial backbone to medical services necessary for everyday living. A global pandemic resulting in critical demand for medications and vaccines was an eye-opener in the current era. The intrinsic complexity among the bodies involved in the supply chain results in a lack of data transparency, security, privacy, and reliable communication. The counterfeited drug is an outcome of such limitations that adversely affects a global population. Consecutively, fair allocation and distribution of drugs and vaccines to administer them to a global mass equally is also a significant concern. Blockchain as technology grants an essential platform to track and manage transactions among communicating parties in the supply chain using a peer-to-peer, secured, distributed ledger, removing the need for intermediaries or entrusted third parties. Most existing studies focus on tracking and tracing supply chain systems in a centralized manner, leading to transparency, authenticity, data privacy, and authenticity concerns in healthcare supply chains. In this article, we propose a FAIR blockchain-based approach deploying smart contracts leading to transparent traceability of data and transactions in the healthcare supply chain between the communicating parties We propose an approach that allows fair allocation and distribution of vaccines as per the demand generated from the global population. We present a system architecture and algorithm representing the communication between parties that governs our proposed approach. We have computed network performance based and blockchain based evaluation of the proposed system. We have calculated the communication and computation cost of 1152 bits and 12.6 ms respectively.
{"title":"FAIR: A Blockchain-based Vaccine Distribution Scheme for Pandemics","authors":"Anuja R. Nair, Rajesh Gupta, S. Tanwar","doi":"10.1109/GCWkshps52748.2021.9682114","DOIUrl":"https://doi.org/10.1109/GCWkshps52748.2021.9682114","url":null,"abstract":"Demand forecasting, supply acquisition in healthcare supply chains are significant concerns spanning various organizations and bodies, rendering a crucial backbone to medical services necessary for everyday living. A global pandemic resulting in critical demand for medications and vaccines was an eye-opener in the current era. The intrinsic complexity among the bodies involved in the supply chain results in a lack of data transparency, security, privacy, and reliable communication. The counterfeited drug is an outcome of such limitations that adversely affects a global population. Consecutively, fair allocation and distribution of drugs and vaccines to administer them to a global mass equally is also a significant concern. Blockchain as technology grants an essential platform to track and manage transactions among communicating parties in the supply chain using a peer-to-peer, secured, distributed ledger, removing the need for intermediaries or entrusted third parties. Most existing studies focus on tracking and tracing supply chain systems in a centralized manner, leading to transparency, authenticity, data privacy, and authenticity concerns in healthcare supply chains. In this article, we propose a FAIR blockchain-based approach deploying smart contracts leading to transparent traceability of data and transactions in the healthcare supply chain between the communicating parties We propose an approach that allows fair allocation and distribution of vaccines as per the demand generated from the global population. We present a system architecture and algorithm representing the communication between parties that governs our proposed approach. We have computed network performance based and blockchain based evaluation of the proposed system. We have calculated the communication and computation cost of 1152 bits and 12.6 ms respectively.","PeriodicalId":6802,"journal":{"name":"2021 IEEE Globecom Workshops (GC Wkshps)","volume":"34 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75211780","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 : 2021-12-01DOI: 10.1109/GCWkshps52748.2021.9682004
Weiyi Wang, Yutao Jiao, Jin Chen, Gui Fang, Yuhua Xu, Yang Zhang
The integration of blockchain technology and Internet of Things (IoT) enables a wide range of business or industrial decentralized applications. However, incentivizing the self-interested IoT devices to participate in the blockchain net-work faces the challenges of the information asymmetry, energy constraints, and the wireless communication environment. In this paper, we focus on the blockchain system deployment in the classical wireless sensor networks (WSN). We design a multi-dimensional contract as the incentive mechanism which aims to maximize the WSN based blockchain operation time and data utilities. In particular, we derive the energy consumption model in maintaining the wireless blockchain network by analyzing the block mining process and the wireless block broadcast features. Moreover, we give the feasible conditions of the contract. Numerical results demonstrate that our proposed contract effectively incentivizes sensors to participate in the consensus process, and maintain the WSN based blockchain effectively from the economics perspective.
{"title":"Multi-Dimensional Contract Design for Blockchain Deployment in WSN under Information Asymmetry","authors":"Weiyi Wang, Yutao Jiao, Jin Chen, Gui Fang, Yuhua Xu, Yang Zhang","doi":"10.1109/GCWkshps52748.2021.9682004","DOIUrl":"https://doi.org/10.1109/GCWkshps52748.2021.9682004","url":null,"abstract":"The integration of blockchain technology and Internet of Things (IoT) enables a wide range of business or industrial decentralized applications. However, incentivizing the self-interested IoT devices to participate in the blockchain net-work faces the challenges of the information asymmetry, energy constraints, and the wireless communication environment. In this paper, we focus on the blockchain system deployment in the classical wireless sensor networks (WSN). We design a multi-dimensional contract as the incentive mechanism which aims to maximize the WSN based blockchain operation time and data utilities. In particular, we derive the energy consumption model in maintaining the wireless blockchain network by analyzing the block mining process and the wireless block broadcast features. Moreover, we give the feasible conditions of the contract. Numerical results demonstrate that our proposed contract effectively incentivizes sensors to participate in the consensus process, and maintain the WSN based blockchain effectively from the economics perspective.","PeriodicalId":6802,"journal":{"name":"2021 IEEE Globecom Workshops (GC Wkshps)","volume":"14 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78215467","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 : 2021-12-01DOI: 10.1109/GCWkshps52748.2021.9682014
J. Bernaola, I. Sobrón, J. Ser, I. Landa, I. Eizmendi, M. Vélez
The detection, location, and behavior recognition of human beings in different environments is not only a subject of a wide range of studies, but has also triggered the development of a large number of applications, including those which enhance sustainability and efficiency of infrastructures. For instance, the estimation of the occupancy could improve the energy management of a building. Due to human presence or movement over a particular area, the analysis of variations in wireless signal properties of already deployed wireless technology such as WiFi systems provides the information needed for Machine Learning models to accomplish the non-intrusive (device-free) detection and classification of different human activities. In this context, this work focuses on detecting seated people in an indoor scenario by using ensemble learning, a particular branch of Machine Learning models for supervised learning that hinges on combining the outputs of individual predictors. Furthermore, we evaluate the transferability of the knowledge modeled by ensemble learners. When trained in a particular frequency or channel, such models are used to classify data captured over another different frequency. Our experimental setup and discussed results reveal that while ensembles attain satisfactory levels of predictive accuracy predictions, their knowledge cannot be transferred among different frequencies. This conclusion opens an exciting future towards new means to perform effective knowledge transfer over the frequency domain.
{"title":"Ensemble Learning for Seated People Counting using WiFi Signals: Performance Study and Transferability Assessment","authors":"J. Bernaola, I. Sobrón, J. Ser, I. Landa, I. Eizmendi, M. Vélez","doi":"10.1109/GCWkshps52748.2021.9682014","DOIUrl":"https://doi.org/10.1109/GCWkshps52748.2021.9682014","url":null,"abstract":"The detection, location, and behavior recognition of human beings in different environments is not only a subject of a wide range of studies, but has also triggered the development of a large number of applications, including those which enhance sustainability and efficiency of infrastructures. For instance, the estimation of the occupancy could improve the energy management of a building. Due to human presence or movement over a particular area, the analysis of variations in wireless signal properties of already deployed wireless technology such as WiFi systems provides the information needed for Machine Learning models to accomplish the non-intrusive (device-free) detection and classification of different human activities. In this context, this work focuses on detecting seated people in an indoor scenario by using ensemble learning, a particular branch of Machine Learning models for supervised learning that hinges on combining the outputs of individual predictors. Furthermore, we evaluate the transferability of the knowledge modeled by ensemble learners. When trained in a particular frequency or channel, such models are used to classify data captured over another different frequency. Our experimental setup and discussed results reveal that while ensembles attain satisfactory levels of predictive accuracy predictions, their knowledge cannot be transferred among different frequencies. This conclusion opens an exciting future towards new means to perform effective knowledge transfer over the frequency domain.","PeriodicalId":6802,"journal":{"name":"2021 IEEE Globecom Workshops (GC Wkshps)","volume":"12 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75899242","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 : 2021-12-01DOI: 10.1109/GCWkshps52748.2021.9682094
G. Raja, Yashvandh Baskar, P. Dhanasekaran, R. Nawaz, Keping Yu
Multiple Unmanned Aerial Vehicles (UAVs) have a greater potential to be widely used in civil and military applications. Swarm of UAVs can be deployed in a multitude of 24/7 security and surveillance. The network management and pattern formation are crucial for multi-UAV formation control mechanisms while cautiously navigating the surveillance areas. A Deep Reinforcement Learning (DRL) based Formation Flight Control for Navigation (FFCN) is used to efficiently build the UAV swarm, which decreases networking load by minimizing communication and processing involved in pattern formation. Moreover, through the leader-follower navigation, the network management of the swarm is substantially simplified. The leader-follower approach in FFCN is efficient for multi-UAV as the navigation system needs to find only the leader's trajectory. However, the failure of the leader due to actuator faults decreases the efficiency of the system. The proposed FFCN addresses the above by including a fault-tolerance mechanism, thus improving the system's reliability. Simulation results show that the FFCN model achieves faster convergence in less time with a lower collision rate. The model's usage reduced the collision rate to 3.4% in successful formation without colliding with other UAVs.
{"title":"An Efficient Formation Control mechanism for Multi-UAV Navigation in Remote Surveillance","authors":"G. Raja, Yashvandh Baskar, P. Dhanasekaran, R. Nawaz, Keping Yu","doi":"10.1109/GCWkshps52748.2021.9682094","DOIUrl":"https://doi.org/10.1109/GCWkshps52748.2021.9682094","url":null,"abstract":"Multiple Unmanned Aerial Vehicles (UAVs) have a greater potential to be widely used in civil and military applications. Swarm of UAVs can be deployed in a multitude of 24/7 security and surveillance. The network management and pattern formation are crucial for multi-UAV formation control mechanisms while cautiously navigating the surveillance areas. A Deep Reinforcement Learning (DRL) based Formation Flight Control for Navigation (FFCN) is used to efficiently build the UAV swarm, which decreases networking load by minimizing communication and processing involved in pattern formation. Moreover, through the leader-follower navigation, the network management of the swarm is substantially simplified. The leader-follower approach in FFCN is efficient for multi-UAV as the navigation system needs to find only the leader's trajectory. However, the failure of the leader due to actuator faults decreases the efficiency of the system. The proposed FFCN addresses the above by including a fault-tolerance mechanism, thus improving the system's reliability. Simulation results show that the FFCN model achieves faster convergence in less time with a lower collision rate. The model's usage reduced the collision rate to 3.4% in successful formation without colliding with other UAVs.","PeriodicalId":6802,"journal":{"name":"2021 IEEE Globecom Workshops (GC Wkshps)","volume":"2 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81847166","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 : 2021-12-01DOI: 10.1109/GCWkshps52748.2021.9682170
M. Banat, J. Bas, A. Dowhuszko
This paper presents a novel physical-layer security approach to protect the information exchanged in a wireless communication system based on OFDM. In this method, QAM symbols that are fed into the IFFT block are split into two subsets. The first subset of symbols is placed on non-scrambled (indexing) subcarriers, whereas the remaining symbols are transmitted on scrambled (data) subcarriers. Based on the bits placed on the indexing subcarriers, a permutation matrix that defines the (data-based) scrambling sequence of the data subcarriers is determined using an algorithm that is known a priori between the transmitter and receiver. The mapping between indexing bits and scrambling sequences is designed to minimize error propagation when there are erroneous received indexing bits (i.e. Gray-mapped sequences). Closed form formulas that approximate the Bit Error Probability (BEP) of the baseline (non-scrambled) and proposed (scrambled) OFDM transmissions are determined for different link configurations. The impact of the proposed physical-layer security scheme on the BEP is minimal, while increasing notably the number of combinations that an eavesdropper must check in order to execute a brute-force search attack.
{"title":"Improved physical-layer security for OFDM using data-based subcarrier scrambling","authors":"M. Banat, J. Bas, A. Dowhuszko","doi":"10.1109/GCWkshps52748.2021.9682170","DOIUrl":"https://doi.org/10.1109/GCWkshps52748.2021.9682170","url":null,"abstract":"This paper presents a novel physical-layer security approach to protect the information exchanged in a wireless communication system based on OFDM. In this method, QAM symbols that are fed into the IFFT block are split into two subsets. The first subset of symbols is placed on non-scrambled (indexing) subcarriers, whereas the remaining symbols are transmitted on scrambled (data) subcarriers. Based on the bits placed on the indexing subcarriers, a permutation matrix that defines the (data-based) scrambling sequence of the data subcarriers is determined using an algorithm that is known a priori between the transmitter and receiver. The mapping between indexing bits and scrambling sequences is designed to minimize error propagation when there are erroneous received indexing bits (i.e. Gray-mapped sequences). Closed form formulas that approximate the Bit Error Probability (BEP) of the baseline (non-scrambled) and proposed (scrambled) OFDM transmissions are determined for different link configurations. The impact of the proposed physical-layer security scheme on the BEP is minimal, while increasing notably the number of combinations that an eavesdropper must check in order to execute a brute-force search attack.","PeriodicalId":6802,"journal":{"name":"2021 IEEE Globecom Workshops (GC Wkshps)","volume":"19 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81856733","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 : 2021-12-01DOI: 10.1109/GCWkshps52748.2021.9681939
Ke Wang, C. Lam, B. Ng
In this paper, we analyze the effects of different types of hardware impairments (HWI), including RIS-HWI, transceiver HWI, phase quantization errors and random failures, on vehicular communication system using reconfigurable intelligent surfaces (RIS) with Doppler mitigation. A closed-form expression for the received signal-to-noise-and-distortion ratio (SNDR) of an RIS-aided vehicular communication system with HWI is derived, and we also show that the average Doppler spread can be removed completely. The simulation results validate that RIS with HWI is able to bring promising average SNDR gain (e.g, 3.16 dB) of the received signal, while eliminating the average Doppler spread, and keeping the delay spread at a very low range. As a result, using the predictable positions of the vehicle, the phase shift set of RIS can be designed in advance, such that channel estimation is not necessary, resulting in lower implementation complexity.
{"title":"Doppler Effect Mitigation using Reconfigurable Intelligent Surfaces with Hardware Impairments","authors":"Ke Wang, C. Lam, B. Ng","doi":"10.1109/GCWkshps52748.2021.9681939","DOIUrl":"https://doi.org/10.1109/GCWkshps52748.2021.9681939","url":null,"abstract":"In this paper, we analyze the effects of different types of hardware impairments (HWI), including RIS-HWI, transceiver HWI, phase quantization errors and random failures, on vehicular communication system using reconfigurable intelligent surfaces (RIS) with Doppler mitigation. A closed-form expression for the received signal-to-noise-and-distortion ratio (SNDR) of an RIS-aided vehicular communication system with HWI is derived, and we also show that the average Doppler spread can be removed completely. The simulation results validate that RIS with HWI is able to bring promising average SNDR gain (e.g, 3.16 dB) of the received signal, while eliminating the average Doppler spread, and keeping the delay spread at a very low range. As a result, using the predictable positions of the vehicle, the phase shift set of RIS can be designed in advance, such that channel estimation is not necessary, resulting in lower implementation complexity.","PeriodicalId":6802,"journal":{"name":"2021 IEEE Globecom Workshops (GC Wkshps)","volume":"55 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84481989","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 : 2021-12-01DOI: 10.1109/GCWkshps52748.2021.9682104
S. Shreyas, J. Rao
The abrupt rise in Coronavirus cases has led to shortage of rapid and highly sensitive reverse transcriptase polymerase chain reaction (RT-PCR) testing kits for the diagnosis of coronavirus disease 2019 (COVID-19). Radiologists have found X-ray images could be useful for diagnosis of COVID. In this work, Diagnostic Decision Support for Medical Imaging (DDSM)++ is introduced to detect the different abnormal conditions in lung including COVID. The scarcity of COVID dataset is handled by using various spatial transform augmentation techniques, such as power law transformation, Gaussian blur, and sharpening. Also, to get the benefit of inference accelerators, an android mobile application is developed which is quantized and optimized for ARM Mali GPU. The DDSM++ model is an extended version of DDSM model (inspired from Densenet-121), and the X-ray images are preprocessed with Contrast Limited Adaptive Histogram Equalization (CLAHE) to improve the quality of X-ray images. The COVID X-ray images are obtained from the open source and the proposed method has obtained almost 98.47% accuracy for COVID detection. Further, the model is quantized to FP-16 using TFLITE and is utilized to benchmark the inference acceleration on Edge devices with ARM Mali GPU. About 30% and 80% reduction in inference time was observed for FP-32 and FP-16 models when run on ARM Mali GPU. Post quantization, about 5% drop in accuracy is observed for COVID detection.
冠状病毒病例的突然增加导致用于诊断2019冠状病毒病(COVID-19)的快速和高灵敏度逆转录酶聚合酶链反应(RT-PCR)检测试剂盒短缺。放射科医生发现x射线图像可能对诊断COVID很有用。本研究引入医学影像诊断决策支持(DDSM)++来检测包括COVID在内的肺部各种异常情况。利用幂律变换、高斯模糊和锐化等多种空间变换增强技术处理COVID数据集的稀缺性。此外，为了充分利用推理加速器的优势，开发了一个针对ARM Mali GPU进行量化优化的android移动应用程序。ddsm++模型是DDSM模型的扩展版本(灵感来自Densenet-121)，采用对比度有限自适应直方图均衡化(CLAHE)对x射线图像进行预处理，以提高x射线图像的质量。新冠肺炎x射线图像来自开源，该方法对新冠肺炎的检测准确率接近98.47%。进一步，使用TFLITE将模型量化到FP-16，并利用ARM Mali GPU对Edge设备上的推理加速进行基准测试。在ARM Mali GPU上运行时，FP-32和FP-16模型的推理时间分别减少了30%和80%。量化后，观察到COVID检测的准确性下降了约5%。
{"title":"Diagnostic Decision Support for Medical Imaging and COVID-19 Image Classification on ARM Mali GPU","authors":"S. Shreyas, J. Rao","doi":"10.1109/GCWkshps52748.2021.9682104","DOIUrl":"https://doi.org/10.1109/GCWkshps52748.2021.9682104","url":null,"abstract":"The abrupt rise in Coronavirus cases has led to shortage of rapid and highly sensitive reverse transcriptase polymerase chain reaction (RT-PCR) testing kits for the diagnosis of coronavirus disease 2019 (COVID-19). Radiologists have found X-ray images could be useful for diagnosis of COVID. In this work, Diagnostic Decision Support for Medical Imaging (DDSM)++ is introduced to detect the different abnormal conditions in lung including COVID. The scarcity of COVID dataset is handled by using various spatial transform augmentation techniques, such as power law transformation, Gaussian blur, and sharpening. Also, to get the benefit of inference accelerators, an android mobile application is developed which is quantized and optimized for ARM Mali GPU. The DDSM++ model is an extended version of DDSM model (inspired from Densenet-121), and the X-ray images are preprocessed with Contrast Limited Adaptive Histogram Equalization (CLAHE) to improve the quality of X-ray images. The COVID X-ray images are obtained from the open source and the proposed method has obtained almost 98.47% accuracy for COVID detection. Further, the model is quantized to FP-16 using TFLITE and is utilized to benchmark the inference acceleration on Edge devices with ARM Mali GPU. About 30% and 80% reduction in inference time was observed for FP-32 and FP-16 models when run on ARM Mali GPU. Post quantization, about 5% drop in accuracy is observed for COVID detection.","PeriodicalId":6802,"journal":{"name":"2021 IEEE Globecom Workshops (GC Wkshps)","volume":"2 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85540565","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 accurate prediction of received signal strength (RSS) is the key to coverage optimization and interference management in network planning, as well as proactive resource allocation and anticipated network management. Traditional methods for RSS prediction are based on ray tracing or stochastic radio propagation model. The former requires the detailed 3D geometry and dielectric properties of the reflectors, which may not be available practically. The latter roughly classify the environment as either urban, suburban and rural scenarios and does not make full use of the environment information. In this paper, by leveraging accessible satellite maps to capture the features of radio environment, a distributed federated learning (FL) RSS prediction framework is proposed to fully exploit the user generated real-time data while preserving the users’ privacy. To further improve the prediction accuracy, the deep vision transformer (DeepVIT) is utilized to process the images of the satellite map, because it is capable of learning to "pay attention to" important parts of an image such as reflection surfaces and blockages. The proposed method is evaluated by the real-world data set including around 60, 000 individual measurements. Simulations results verified that the prediction accuracy of the proposed method outperforms baseline methods including ray tracing, Urban Macro (UMa) model and convolutional neural network (CNN) based method. Moreover, the computational time is reduced five times compared with CNN based method.
{"title":"Distributed Signal Strength Prediction using Satellite Map empowered by Deep Vision Transformer","authors":"Haiyao Yu, Zhanwei Hou, Yifan Gu, Peng Cheng, Wanli Ouyang, Yonghui Li, B. Vucetic","doi":"10.1109/GCWkshps52748.2021.9682021","DOIUrl":"https://doi.org/10.1109/GCWkshps52748.2021.9682021","url":null,"abstract":"The accurate prediction of received signal strength (RSS) is the key to coverage optimization and interference management in network planning, as well as proactive resource allocation and anticipated network management. Traditional methods for RSS prediction are based on ray tracing or stochastic radio propagation model. The former requires the detailed 3D geometry and dielectric properties of the reflectors, which may not be available practically. The latter roughly classify the environment as either urban, suburban and rural scenarios and does not make full use of the environment information. In this paper, by leveraging accessible satellite maps to capture the features of radio environment, a distributed federated learning (FL) RSS prediction framework is proposed to fully exploit the user generated real-time data while preserving the users’ privacy. To further improve the prediction accuracy, the deep vision transformer (DeepVIT) is utilized to process the images of the satellite map, because it is capable of learning to \"pay attention to\" important parts of an image such as reflection surfaces and blockages. The proposed method is evaluated by the real-world data set including around 60, 000 individual measurements. Simulations results verified that the prediction accuracy of the proposed method outperforms baseline methods including ray tracing, Urban Macro (UMa) model and convolutional neural network (CNN) based method. Moreover, the computational time is reduced five times compared with CNN based method.","PeriodicalId":6802,"journal":{"name":"2021 IEEE Globecom Workshops (GC Wkshps)","volume":"405 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76623587","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 : 2021-12-01DOI: 10.1109/GCWkshps52748.2021.9681977
Fan Yang, Jianwei Tian, Tao Feng, Fangmin Xu, Chao Qiu, Chenglin Zhao
Recently, parallel reinforcement learning (PRL) based Industrial Internet of Things (IIoT) edge-cloud resource scheduling has elicited escalating attention. However, with the scale of IIoT expands, there are several challenges in the existing researches: 1) large number of parallel servers slows down the convergence rate of PRL; 2) malicious parallel server affects resource allocation efficiency. In order to solve the above efficiency and security problem, blockchain-based approaches are introduced in PRL based resource allocation problem. However, traditional consensus algorithm in blockchain is not suitable for resource allocation and is inefficient. Thus, in this article, based on a novel fuzzy delegated proof of state and practical byzantine fault tolerance (fuzzy DPoSt+PBFT) consensus algorithm, we propose a blockchain-enabled collaborative parallel Q-learning (CPQL) approach to address the above challenges. To be specific, we first construct an edge-cloud collaborative architecture for executing the diversity intelligence IIoT applications. Then, we propose a CPQL algorithm for edge-cloud resource allocation and choosing the optimal number of parallel edge servers to speed up the Q-table training. In the Q-table aggregation process in CPQL, a fuzzy DPoSt+PBFT algorithm is designed for secure CPQL training and efficient consensus. Experimental results show the superior performance of the proposed approach. And the proposed approach has great potential in IIoT resource allocation problem.
{"title":"Blockchain-Enabled Parallel Learning in Industrial Edge-Cloud Network: a Fuzzy DPoSt-PBFT Approach","authors":"Fan Yang, Jianwei Tian, Tao Feng, Fangmin Xu, Chao Qiu, Chenglin Zhao","doi":"10.1109/GCWkshps52748.2021.9681977","DOIUrl":"https://doi.org/10.1109/GCWkshps52748.2021.9681977","url":null,"abstract":"Recently, parallel reinforcement learning (PRL) based Industrial Internet of Things (IIoT) edge-cloud resource scheduling has elicited escalating attention. However, with the scale of IIoT expands, there are several challenges in the existing researches: 1) large number of parallel servers slows down the convergence rate of PRL; 2) malicious parallel server affects resource allocation efficiency. In order to solve the above efficiency and security problem, blockchain-based approaches are introduced in PRL based resource allocation problem. However, traditional consensus algorithm in blockchain is not suitable for resource allocation and is inefficient. Thus, in this article, based on a novel fuzzy delegated proof of state and practical byzantine fault tolerance (fuzzy DPoSt+PBFT) consensus algorithm, we propose a blockchain-enabled collaborative parallel Q-learning (CPQL) approach to address the above challenges. To be specific, we first construct an edge-cloud collaborative architecture for executing the diversity intelligence IIoT applications. Then, we propose a CPQL algorithm for edge-cloud resource allocation and choosing the optimal number of parallel edge servers to speed up the Q-table training. In the Q-table aggregation process in CPQL, a fuzzy DPoSt+PBFT algorithm is designed for secure CPQL training and efficient consensus. Experimental results show the superior performance of the proposed approach. And the proposed approach has great potential in IIoT resource allocation problem.","PeriodicalId":6802,"journal":{"name":"2021 IEEE Globecom Workshops (GC Wkshps)","volume":"93 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77208600","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 : 2021-12-01DOI: 10.1109/GCWkshps52748.2021.9682115
Sung Hyuck Hong, Junil Choi
Intelligent reflecting surface (IRS) has been recently proposed as a promising technology to improve the spectral and energy efficiency of future wireless networks by establishing the favorable communication environments in a cost-effective manner. In this paper, we propose the phase shift design for IRS-aided millimeter wave (mmWave) communication systems that employ large antenna arrays at the transceivers. By leveraging the angular sparsity and large dimension of mmWave channels, the proposed phase shift design can significantly enhance the spectral efficiency of mmWave multiple-input multiple-output (MIMO) systems. Simulation results verify that the proposed phase shift design outperforms the existing benchmarks.
{"title":"Phase Shift Design for Intelligent Reflecting Surface Aided mmWave MIMO Systems","authors":"Sung Hyuck Hong, Junil Choi","doi":"10.1109/GCWkshps52748.2021.9682115","DOIUrl":"https://doi.org/10.1109/GCWkshps52748.2021.9682115","url":null,"abstract":"Intelligent reflecting surface (IRS) has been recently proposed as a promising technology to improve the spectral and energy efficiency of future wireless networks by establishing the favorable communication environments in a cost-effective manner. In this paper, we propose the phase shift design for IRS-aided millimeter wave (mmWave) communication systems that employ large antenna arrays at the transceivers. By leveraging the angular sparsity and large dimension of mmWave channels, the proposed phase shift design can significantly enhance the spectral efficiency of mmWave multiple-input multiple-output (MIMO) systems. Simulation results verify that the proposed phase shift design outperforms the existing benchmarks.","PeriodicalId":6802,"journal":{"name":"2021 IEEE Globecom Workshops (GC Wkshps)","volume":"425 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86848073","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：