Long Range (LoRa) technology is gaining considerable academic and commercial traction because of its potential for low power consumption, long transmission distance and wide coverage. In this paper, we focus on the effect of residual carrier frequency offset (RCFO) on LoRa systems, and fill in the blank of efficient estimation and compensation algorithm. We first provide mathematically description of the LoRa signal with RCFO and derive the modulus of the correlation function between the RCFO precompensated upchirp in preamble and the local upchirp. Then, we propose an efficient RCFO estimation algorithm based on the Golden Section Search. The simulation results show that compared with the traditional method, our method achieves higher accuracy of the RCFO estimation and restore the Bit Error Rate (BER) to an acceptable level after compensation.
{"title":"A Novel Residual Carrier Frequency Offset Estimation Approach for LoRa Systems","authors":"Pengxin Guan, Hongkang Yu, Hongfei Zhu, Yuping Zhao","doi":"10.1109/ICCCS49078.2020.9118416","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118416","url":null,"abstract":"Long Range (LoRa) technology is gaining considerable academic and commercial traction because of its potential for low power consumption, long transmission distance and wide coverage. In this paper, we focus on the effect of residual carrier frequency offset (RCFO) on LoRa systems, and fill in the blank of efficient estimation and compensation algorithm. We first provide mathematically description of the LoRa signal with RCFO and derive the modulus of the correlation function between the RCFO precompensated upchirp in preamble and the local upchirp. Then, we propose an efficient RCFO estimation algorithm based on the Golden Section Search. The simulation results show that compared with the traditional method, our method achieves higher accuracy of the RCFO estimation and restore the Bit Error Rate (BER) to an acceptable level after compensation.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122233192","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 : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118478
Hui Wang, Li Ma, Hongying Bai
Wireless sensor network (WSN) is a wireless self-organizing multi-hop network that can sense and collect the information of the monitored environment through a certain number of sensor nodes which deployed in a certain area and transmit the collected information to the client. Due to the limited power and data capacity stored by the micro sensor, it is weak in communication with other nodes, data storage and calculation, and is very vulnerable to attack and harm to the entire network. The Sybil attack is a classic example. Sybil attack refers to the attack in which malicious nodes forge multiple node identities to participate in network operation. Malicious attackers can forge multiple node identities to participate in data forwarding. So that the data obtained by the end user without any use value. In this paper, we propose a three-tier detection scheme for the Sybil node in the severe environment. Every sensor node will determine whether they are Sybil nodes through the first-level and second-level high-energy node detection. Finally, the base station determines whether the Sybil node detected by the first two stages is true Sybil node. The simulation results show that our proposed scheme significantly improves network lifetime, and effectively improves the accuracy of Sybil node detection.
{"title":"A Three-tier Scheme for Sybil Attack Detection in Wireless Sensor Networks","authors":"Hui Wang, Li Ma, Hongying Bai","doi":"10.1109/ICCCS49078.2020.9118478","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118478","url":null,"abstract":"Wireless sensor network (WSN) is a wireless self-organizing multi-hop network that can sense and collect the information of the monitored environment through a certain number of sensor nodes which deployed in a certain area and transmit the collected information to the client. Due to the limited power and data capacity stored by the micro sensor, it is weak in communication with other nodes, data storage and calculation, and is very vulnerable to attack and harm to the entire network. The Sybil attack is a classic example. Sybil attack refers to the attack in which malicious nodes forge multiple node identities to participate in network operation. Malicious attackers can forge multiple node identities to participate in data forwarding. So that the data obtained by the end user without any use value. In this paper, we propose a three-tier detection scheme for the Sybil node in the severe environment. Every sensor node will determine whether they are Sybil nodes through the first-level and second-level high-energy node detection. Finally, the base station determines whether the Sybil node detected by the first two stages is true Sybil node. The simulation results show that our proposed scheme significantly improves network lifetime, and effectively improves the accuracy of Sybil node detection.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133852172","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 : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118564
Songchenchen Gong, E. Bourennane, Junyu Gao
The crowd counting task is an important research problem. Now more and more people are concerned about safety issues. When the population density reaches a very high peak, the population density counts, the alarm is sent out, and the crowds are diverted. The trampling of the Shanghai New Year’s stampede will not happen again. The final density map is produced by two steps: at first, extract feature maps from multiple layers, and then adjust their output so that they are all the same size, all these resized layers are combined into the final density map. We also used texture features and target edge detection to reduce the loss of density map detail to better integrate with our convolutional neural network. We tested on several commonly used datasets. Our model achieved good results in crowd counting.
{"title":"Multi-feature Counting of Dense Crowd Image Based on Multi-column Convolutional Neural Network","authors":"Songchenchen Gong, E. Bourennane, Junyu Gao","doi":"10.1109/ICCCS49078.2020.9118564","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118564","url":null,"abstract":"The crowd counting task is an important research problem. Now more and more people are concerned about safety issues. When the population density reaches a very high peak, the population density counts, the alarm is sent out, and the crowds are diverted. The trampling of the Shanghai New Year’s stampede will not happen again. The final density map is produced by two steps: at first, extract feature maps from multiple layers, and then adjust their output so that they are all the same size, all these resized layers are combined into the final density map. We also used texture features and target edge detection to reduce the loss of density map detail to better integrate with our convolutional neural network. We tested on several commonly used datasets. Our model achieved good results in crowd counting.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"25 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133195971","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 : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118566
Zukun Lu, Feiqiang Chen, Yuchen Xie, Zhe Liu
The performance of anti-jamming is limited by channel mismatch in antenna arrays navigation receivers. Under the same radio frequency (RF) channel characteristic, this paper has analyzed the influence on anti-jamming performance in different global navigation satellite system (GNSS) signal bandwidth. Increasing the bandwidth of signal is an effective way to improve the positioning accuracy in satellite navigation. According to the simulation and experiment in the case of channel mismatch, increasing the signal bandwidth would lead to anti-jamming performance degradation, which is seriously lack of theoretical support. In this paper, we derive the weight value of space-time adaptive processor (STAP) and the transfer function, and the influence of signal bandwidth to anti-jamming performance is analyzed. The theoretical analysis shows that increasing signal bandwidth would lead to anti-jamming performance degradation under the condition of channel mismatch.
{"title":"Impact on Anti-jamming Performance of GNSS Signal Bandwidth under Channel Mismatch Used Antenna Arrays","authors":"Zukun Lu, Feiqiang Chen, Yuchen Xie, Zhe Liu","doi":"10.1109/ICCCS49078.2020.9118566","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118566","url":null,"abstract":"The performance of anti-jamming is limited by channel mismatch in antenna arrays navigation receivers. Under the same radio frequency (RF) channel characteristic, this paper has analyzed the influence on anti-jamming performance in different global navigation satellite system (GNSS) signal bandwidth. Increasing the bandwidth of signal is an effective way to improve the positioning accuracy in satellite navigation. According to the simulation and experiment in the case of channel mismatch, increasing the signal bandwidth would lead to anti-jamming performance degradation, which is seriously lack of theoretical support. In this paper, we derive the weight value of space-time adaptive processor (STAP) and the transfer function, and the influence of signal bandwidth to anti-jamming performance is analyzed. The theoretical analysis shows that increasing signal bandwidth would lead to anti-jamming performance degradation under the condition of channel mismatch.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132242413","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 : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118505
Huayan Pei, Guanghui Yan, Huanmin Wang
In cooperation dilemmas, for cooperation to emerge, a mechanism for the evolution of cooperation is needed. We propose a costly monetary punishment model based on the spatial prisoner’s dilemma game and complex networks, specifically, cooperators sanction defective behaviors by applying a punishment fine to defectors directly, and all cooperators share the punishment cost. We mainly focus on how the monetary punishment mechanism affects the evolution of individuals’ strategy behaviors under different network structures. Results show that cooperation is significantly promoted even for quite small initial fractions of cooperators in square lattice and small-world network. Furthermore, we find out that when the mechanism is turned off, cooperation drops to a comparatively lower level in small-world network, while there is no change in square lattice. Additionally, the mechanism promotes the average payoff of the population.
{"title":"Monetary Punishment Promotes Cooperation in Complex Networks","authors":"Huayan Pei, Guanghui Yan, Huanmin Wang","doi":"10.1109/ICCCS49078.2020.9118505","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118505","url":null,"abstract":"In cooperation dilemmas, for cooperation to emerge, a mechanism for the evolution of cooperation is needed. We propose a costly monetary punishment model based on the spatial prisoner’s dilemma game and complex networks, specifically, cooperators sanction defective behaviors by applying a punishment fine to defectors directly, and all cooperators share the punishment cost. We mainly focus on how the monetary punishment mechanism affects the evolution of individuals’ strategy behaviors under different network structures. Results show that cooperation is significantly promoted even for quite small initial fractions of cooperators in square lattice and small-world network. Furthermore, we find out that when the mechanism is turned off, cooperation drops to a comparatively lower level in small-world network, while there is no change in square lattice. Additionally, the mechanism promotes the average payoff of the population.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132406403","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 : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118517
Abdallah Tubaishat, Mariam Al Jouhi
Smart cities have evolved in the last years, leading the cities to implement initiatives related to technical aspects to improve quality of life. City-rankings have become a central tool for assessing the attractiveness of urban regions. The development of smart cities, however, is not without risk. Cities and citizens are putting more and more responsibilities in urban systems. Hence, all key stakeholders should provide an effective safety and security response to any situation affecting their citizens or organizations. Special attention should be paid with respect to development of services aimed at reducing cybercrime. To prevent this, we believe that a better understanding of smart cities and their privacy implications is needed. The paper provides an overview of security aspects of a cyber security in smart cities. It starts with exploration of various definitions, threats, and risks in cyber security as well as threats from environments both internal and external and how these threats are currently mitigated with tools, processes and technologies as smart cities utilizes IoT with big data. Presently, most of the data is transmitted and collected online. Hackers usually try to exploit the vulnerabilities using various tools in order to know more about the customers and then misuse the customer’s information. Enterprises, on the other hand, continue to collect more information in order to improve services, infrastructure, and security. They collect tons of data from customers in order to complete their requirements for the different services they provide. The main concern with the collected data is that it can be vulnerable to misuse by hackers. Building a security framework based on concepts and repositories of big data and leveraging on the intelligence of predictive analytics can help build a security system that can counter these threats and help to guard from these risk and threats to a large extent. Various concepts, applications, and technologies interact to cover every aspect of the digital citizen’s life. Understanding this privacy-challenging environment is the basic requirement for the development of effective protection mechanisms. Thus, the paper aims to address sentiments on cyber security technologies and cybercrime awareness in order to come up with recommendations for innovative solutions. A survey has been conducted and the findings have been analyzed of a case study to come up with recommendations for building a conceptualizing security framework for smart cities. The survey is conducted in the United Arab Emirates (UAE), one of the most advanced countries in the MENA region, who is applying smart city concepts.
{"title":"Building a Security Framework for Smart Cities: A Case Study from UAE","authors":"Abdallah Tubaishat, Mariam Al Jouhi","doi":"10.1109/ICCCS49078.2020.9118517","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118517","url":null,"abstract":"Smart cities have evolved in the last years, leading the cities to implement initiatives related to technical aspects to improve quality of life. City-rankings have become a central tool for assessing the attractiveness of urban regions. The development of smart cities, however, is not without risk. Cities and citizens are putting more and more responsibilities in urban systems. Hence, all key stakeholders should provide an effective safety and security response to any situation affecting their citizens or organizations. Special attention should be paid with respect to development of services aimed at reducing cybercrime. To prevent this, we believe that a better understanding of smart cities and their privacy implications is needed. The paper provides an overview of security aspects of a cyber security in smart cities. It starts with exploration of various definitions, threats, and risks in cyber security as well as threats from environments both internal and external and how these threats are currently mitigated with tools, processes and technologies as smart cities utilizes IoT with big data. Presently, most of the data is transmitted and collected online. Hackers usually try to exploit the vulnerabilities using various tools in order to know more about the customers and then misuse the customer’s information. Enterprises, on the other hand, continue to collect more information in order to improve services, infrastructure, and security. They collect tons of data from customers in order to complete their requirements for the different services they provide. The main concern with the collected data is that it can be vulnerable to misuse by hackers. Building a security framework based on concepts and repositories of big data and leveraging on the intelligence of predictive analytics can help build a security system that can counter these threats and help to guard from these risk and threats to a large extent. Various concepts, applications, and technologies interact to cover every aspect of the digital citizen’s life. Understanding this privacy-challenging environment is the basic requirement for the development of effective protection mechanisms. Thus, the paper aims to address sentiments on cyber security technologies and cybercrime awareness in order to come up with recommendations for innovative solutions. A survey has been conducted and the findings have been analyzed of a case study to come up with recommendations for building a conceptualizing security framework for smart cities. The survey is conducted in the United Arab Emirates (UAE), one of the most advanced countries in the MENA region, who is applying smart city concepts.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133761740","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 : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118528
Guodong Li, Qiuyi Zhang, Rongrong Zheng, Chenhui Wang
A large number of typical fault cases accumulated in the informatization work of State Grid Corporation of China are mostly descriptive text data, which is difficult to understand and analyze by means of automation. In view of this problem, text mining technology is used to extract fault problems and causes from fault cases to form the causal relationship of faults, so as to provide necessary conditions for the next step of fault text mining. This system uses the method of text clustering for fault location and auxiliary research. First of all,do the segmentation of fault information and processing scheme, in this step, the Chinese word segmentation is carried out by using the Jieba word segmentation tool. Secondly, it is necessary to clean the segmentation results and build a corpus. Thirdly, in order to represent the corpus as the type that the computer can calculate the similarity, we need to transform the corpus into frequency matrix. And then instead of using traditional k-means clustering algorithm to cluster, we use the calinski_harabaz score to evaluate the best value of K. Finally, we put this model into application in actual production, build the fault information and solution mapping table.
{"title":"A Fault Analysis Method Based on Text Clustering","authors":"Guodong Li, Qiuyi Zhang, Rongrong Zheng, Chenhui Wang","doi":"10.1109/ICCCS49078.2020.9118528","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118528","url":null,"abstract":"A large number of typical fault cases accumulated in the informatization work of State Grid Corporation of China are mostly descriptive text data, which is difficult to understand and analyze by means of automation. In view of this problem, text mining technology is used to extract fault problems and causes from fault cases to form the causal relationship of faults, so as to provide necessary conditions for the next step of fault text mining. This system uses the method of text clustering for fault location and auxiliary research. First of all,do the segmentation of fault information and processing scheme, in this step, the Chinese word segmentation is carried out by using the Jieba word segmentation tool. Secondly, it is necessary to clean the segmentation results and build a corpus. Thirdly, in order to represent the corpus as the type that the computer can calculate the similarity, we need to transform the corpus into frequency matrix. And then instead of using traditional k-means clustering algorithm to cluster, we use the calinski_harabaz score to evaluate the best value of K. Finally, we put this model into application in actual production, build the fault information and solution mapping table.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"2017 25","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132679654","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 : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118409
Wei Hu, S. Geng, Xiongwen Zhao
In this paper, based on mm-wave 60 GHz channel measurements performed in large hall and corridor for both LoS and NLoS scenarios, channel fading effects like received power, path loss and shadowing are investigated based on radial basis function (RBF) neural network model. Results show that RBF model can fit measurement data better than traditional back propagation (BP) machine learning (ML) method with larger coefficient of determination and smaller root mean square error (RMSE). Neural network models can accurately predict channel parameters, indicates the advances of ML in channel modeling. The presented results are useful in design of 5G wireless communication systems and system development.
{"title":"Mm-Wave 60 GHz Channel Fading Effects Analysis Based on RBF Neural Network","authors":"Wei Hu, S. Geng, Xiongwen Zhao","doi":"10.1109/ICCCS49078.2020.9118409","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118409","url":null,"abstract":"In this paper, based on mm-wave 60 GHz channel measurements performed in large hall and corridor for both LoS and NLoS scenarios, channel fading effects like received power, path loss and shadowing are investigated based on radial basis function (RBF) neural network model. Results show that RBF model can fit measurement data better than traditional back propagation (BP) machine learning (ML) method with larger coefficient of determination and smaller root mean square error (RMSE). Neural network models can accurately predict channel parameters, indicates the advances of ML in channel modeling. The presented results are useful in design of 5G wireless communication systems and system development.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114319721","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 : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118425
Qi Li, Aihua Zhang, Jianjun Li, Bing Ning
This paper proposes a multiple-input multiple-output (MIMO) soft decision signal detection method for a timevarying communication system. In this algorithm, the training samples, including system channel state information and received data, are input to a deep neural network (DNN), and then we employ cross-entropy loss function and root mean square propagation (RMSProp) descent algorithm to offline train and optimize the parameters of the DNN. Besides, the output layer of the DNN uses the sigmoid function as the activation function, and the negative value of the input value of the sigmoid function is the log-likelihood ratio (LLR). In this way, we can obtain the LLR value via removing the sigmoid function during the online testing without the complicated process of calculating the LLR value. Combining the DNN with the soft decision technology improves signal detection performance. Simulation results show that the proposed algorithm is better than the MMSE algorithm and similar to ML algorithm.
{"title":"Soft Decision Signal Detection of MIMO System Based on Deep Neural Network","authors":"Qi Li, Aihua Zhang, Jianjun Li, Bing Ning","doi":"10.1109/ICCCS49078.2020.9118425","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118425","url":null,"abstract":"This paper proposes a multiple-input multiple-output (MIMO) soft decision signal detection method for a timevarying communication system. In this algorithm, the training samples, including system channel state information and received data, are input to a deep neural network (DNN), and then we employ cross-entropy loss function and root mean square propagation (RMSProp) descent algorithm to offline train and optimize the parameters of the DNN. Besides, the output layer of the DNN uses the sigmoid function as the activation function, and the negative value of the input value of the sigmoid function is the log-likelihood ratio (LLR). In this way, we can obtain the LLR value via removing the sigmoid function during the online testing without the complicated process of calculating the LLR value. Combining the DNN with the soft decision technology improves signal detection performance. Simulation results show that the proposed algorithm is better than the MMSE algorithm and similar to ML algorithm.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116353250","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 : 2020-05-01DOI: 10.1109/ICCCS49078.2020.9118490
Zeng Rui, H. Yin, Jinyan Cai
The key problem that must be solved in the analysis and prediction of customer churn in telecom companies is the data completion of customer missing. In this paper, a model based on factor analysis and data mining is proposed to complete customer missing data. This model first completes the factors generated by the missing data, and then completes the missing data. In factor completion, the improved k-mean algorithm is used to effectively solve the problem of initial value and K value selection, and the Euclidean distance is improved to achieve effective clustering of factors and factor completion. The missing data value is obtained by factor reverse reasoning. The model is trained with real historical data and tested to verify that the model is effective.
{"title":"Research on the Model of Missing Information Completion of Telecom Customers Based on Factor Analysis and Data Mining","authors":"Zeng Rui, H. Yin, Jinyan Cai","doi":"10.1109/ICCCS49078.2020.9118490","DOIUrl":"https://doi.org/10.1109/ICCCS49078.2020.9118490","url":null,"abstract":"The key problem that must be solved in the analysis and prediction of customer churn in telecom companies is the data completion of customer missing. In this paper, a model based on factor analysis and data mining is proposed to complete customer missing data. This model first completes the factors generated by the missing data, and then completes the missing data. In factor completion, the improved k-mean algorithm is used to effectively solve the problem of initial value and K value selection, and the Euclidean distance is improved to achieve effective clustering of factors and factor completion. The missing data value is obtained by factor reverse reasoning. The model is trained with real historical data and tested to verify that the model is effective.","PeriodicalId":105556,"journal":{"name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","volume":"377 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131807248","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：