Gang Li, Chunjing Hu, Tao Peng, Xiaohui Zhou, Yueqing Xu
Wireless network nodes equipping multi-radio interfaces on each node and using multi-channel for transmission can greatly enhance the network performance. In this paper, we study the channel assignment problem in the multi-radio multi-channel wireless networks that involves assigning channels to radio interfaces for increasing the throughput of the networks. We propose a channel assignment algorithm which first establishes priorities for nodes, and assigns channels to links according to the priority of links on the same node, called HPMI (High-Priority Minimum-Interference). And the algorithm can connect nodes within each other's communication range with minimal interference. In addition, we developed a method to determine the performance of channel assignment algorithms, in which CSMA/CA is used to avoid the competition of co-channel, and proved that HPMI can provide large reduction in interference and lead to significant gains in throughput.
{"title":"High-Priority Minimum-Interference Channel Assignment in Multi-Radio Multi-Channel Wireless Networks","authors":"Gang Li, Chunjing Hu, Tao Peng, Xiaohui Zhou, Yueqing Xu","doi":"10.1145/3291842.3291880","DOIUrl":"https://doi.org/10.1145/3291842.3291880","url":null,"abstract":"Wireless network nodes equipping multi-radio interfaces on each node and using multi-channel for transmission can greatly enhance the network performance. In this paper, we study the channel assignment problem in the multi-radio multi-channel wireless networks that involves assigning channels to radio interfaces for increasing the throughput of the networks. We propose a channel assignment algorithm which first establishes priorities for nodes, and assigns channels to links according to the priority of links on the same node, called HPMI (High-Priority Minimum-Interference). And the algorithm can connect nodes within each other's communication range with minimal interference. In addition, we developed a method to determine the performance of channel assignment algorithms, in which CSMA/CA is used to avoid the competition of co-channel, and proved that HPMI can provide large reduction in interference and lead to significant gains in throughput.","PeriodicalId":283197,"journal":{"name":"Proceedings of the 2nd International Conference on Telecommunications and Communication Engineering","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125716697","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 novel dual-band orthogonal-polarized filtering antenna array is proposed by utilizing proximity-coupled microstrip feed in this paper. Independent patches with different sizes are designed to implement dual-band orthogonal-polarized radiation, which ensures the good isolation property. U and L resonators are introduced into the series-feeding network, so that two separated arrays can be fed by only one open-circuit microstrip line. Proximity-coupled feeding mechanism also ensures the moderate bandwidth. Good bandpass responses with high frequency selectivity are achieved simultaneously over dual-band. A 2-element orthogonal-polarized array operating at 4.5GHz and 5.0GHz is designed. The bandwidths of 3.8 percent and 4.4 percent, high gain of 7.5dBi and 8.0dBi and good bandpass property have been achieved in the two bands, respectively. Isolation between two operating bands is quite good. Because of the simple feeding network, this small array can easily be expanded into large arrays.
{"title":"A Proximity-coupled Dual-band Orthogonal-polarized Filtering Antenna Array","authors":"Yuemin Wu, Min Wang, Yixuan Li, Wen Wu","doi":"10.1145/3291842.3291846","DOIUrl":"https://doi.org/10.1145/3291842.3291846","url":null,"abstract":"A novel dual-band orthogonal-polarized filtering antenna array is proposed by utilizing proximity-coupled microstrip feed in this paper. Independent patches with different sizes are designed to implement dual-band orthogonal-polarized radiation, which ensures the good isolation property. U and L resonators are introduced into the series-feeding network, so that two separated arrays can be fed by only one open-circuit microstrip line. Proximity-coupled feeding mechanism also ensures the moderate bandwidth. Good bandpass responses with high frequency selectivity are achieved simultaneously over dual-band. A 2-element orthogonal-polarized array operating at 4.5GHz and 5.0GHz is designed. The bandwidths of 3.8 percent and 4.4 percent, high gain of 7.5dBi and 8.0dBi and good bandpass property have been achieved in the two bands, respectively. Isolation between two operating bands is quite good. Because of the simple feeding network, this small array can easily be expanded into large arrays.","PeriodicalId":283197,"journal":{"name":"Proceedings of the 2nd International Conference on Telecommunications and Communication Engineering","volume":"08 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130566235","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In recent years, many researchers have focused on fiber Brillouin amplifier(FBA) for the higher amplify gain than traditional optical amplifiers, such as Erbium-doped fiber amplifier (EDFA). But the efficiency depends deeply on the relative state of polarization (SOP) of pump and probe signal. In this paper, The SOP of pump and probe signal are considered when trying to get the analytical solutions for the steady-state fiber Brillouin amplification in a long single mode optical fiber. The analytical solutions' validity has been proved by comparing with the numerical results. In the experiment, we screen out different amplified probe power through changing the relative SOP of the pump and probe signal.
{"title":"Polarization Properties Analysis for Fiber Brillouin Amplifier","authors":"Kuanlin Mu, Yaojun Qiao, Song Yu, Jianming Shang","doi":"10.1145/3291842.3291915","DOIUrl":"https://doi.org/10.1145/3291842.3291915","url":null,"abstract":"In recent years, many researchers have focused on fiber Brillouin amplifier(FBA) for the higher amplify gain than traditional optical amplifiers, such as Erbium-doped fiber amplifier (EDFA). But the efficiency depends deeply on the relative state of polarization (SOP) of pump and probe signal. In this paper, The SOP of pump and probe signal are considered when trying to get the analytical solutions for the steady-state fiber Brillouin amplification in a long single mode optical fiber. The analytical solutions' validity has been proved by comparing with the numerical results. In the experiment, we screen out different amplified probe power through changing the relative SOP of the pump and probe signal.","PeriodicalId":283197,"journal":{"name":"Proceedings of the 2nd International Conference on Telecommunications and Communication Engineering","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133221169","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}
Yousif A. Alhaj, W. U. Wickramaarachchi, Aamir Hussain, M. A. Al-qaness, Hammam M. Abdelaal
This paper is based on the influence of the frequency of words in the classification of Arabic documents, its effects on the representation of characteristics namely Bag of word (Bow) and Term frequency- Inverse Documents Frequency (TF-IDF). Three classification techniques are being discussed, namely Naive Bayes (NB), k-nearest Neighbor (KNN) and Support Vector Machine (SVM). The Chi-square is used as a selection function to select essential features and remove unnecessary features. An experiment in the classification of Arab documents of public data collected from Arab sites, namely the CNN Arabic Corpus, to study the performance of the classification. The K-fold to validate the classifier and The F1-Micro to test the classifier. Recent results show that SVM classifier was upgraded to KNN and NB classifiers using the TF-IDF representation approach and that the NB classifier outperformed the KNN and SVM classifiers when using the representation approach in Bow. The SVM and NB classifiers attached 94.38% and 93.47% Micro-F1 are worth eliminating the word.
{"title":"Efficient Feature Representation Based on the Effect of Words Frequency for Arabic Documents Classification","authors":"Yousif A. Alhaj, W. U. Wickramaarachchi, Aamir Hussain, M. A. Al-qaness, Hammam M. Abdelaal","doi":"10.1145/3291842.3291900","DOIUrl":"https://doi.org/10.1145/3291842.3291900","url":null,"abstract":"This paper is based on the influence of the frequency of words in the classification of Arabic documents, its effects on the representation of characteristics namely Bag of word (Bow) and Term frequency- Inverse Documents Frequency (TF-IDF). Three classification techniques are being discussed, namely Naive Bayes (NB), k-nearest Neighbor (KNN) and Support Vector Machine (SVM). The Chi-square is used as a selection function to select essential features and remove unnecessary features. An experiment in the classification of Arab documents of public data collected from Arab sites, namely the CNN Arabic Corpus, to study the performance of the classification. The K-fold to validate the classifier and The F1-Micro to test the classifier. Recent results show that SVM classifier was upgraded to KNN and NB classifiers using the TF-IDF representation approach and that the NB classifier outperformed the KNN and SVM classifiers when using the representation approach in Bow. The SVM and NB classifiers attached 94.38% and 93.47% Micro-F1 are worth eliminating the word.","PeriodicalId":283197,"journal":{"name":"Proceedings of the 2nd International Conference on Telecommunications and Communication Engineering","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123939988","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}
As one of the main technologies in 5G networks, Ultra-dense networks (UDNs) can be used to improve the network coverage. The dense deployment of small cells in UDN hotspots generates an uneven traffic distribution. In this paper, we propose a novel mechanism in order to transfer the extra users from the small cells to the macrocells based on several load balancing approaches implemented within the small cells, which are formed based on the Radio-over-Fiber (RoF) system. To select the best overlapping zone and then the best candidate user to be handed-over between the access points of the small cells, a common zone approach, a worst zone approach and a mixed approach are proposed. With the objective of transferring the extra users to the macrocells, we suggest a transfer after approach, a transfer before approach and an active approach. The simulation results indicate that the proposed approaches succeed to balance the load among the access points and to migrate the required load from the overloaded small cells to the macrocells in selective way. In some cases, the balance improvement ratio can reach 97.94%. Moreover, the overall balance efficiency is increased by 51.32% compared to the case without transferring users to the macrocells.
{"title":"Load Migration Mechanism in Ultra-Dense Networks","authors":"M. Salhani, M. Liinaharja","doi":"10.1145/3291842.3291923","DOIUrl":"https://doi.org/10.1145/3291842.3291923","url":null,"abstract":"As one of the main technologies in 5G networks, Ultra-dense networks (UDNs) can be used to improve the network coverage. The dense deployment of small cells in UDN hotspots generates an uneven traffic distribution. In this paper, we propose a novel mechanism in order to transfer the extra users from the small cells to the macrocells based on several load balancing approaches implemented within the small cells, which are formed based on the Radio-over-Fiber (RoF) system. To select the best overlapping zone and then the best candidate user to be handed-over between the access points of the small cells, a common zone approach, a worst zone approach and a mixed approach are proposed. With the objective of transferring the extra users to the macrocells, we suggest a transfer after approach, a transfer before approach and an active approach. The simulation results indicate that the proposed approaches succeed to balance the load among the access points and to migrate the required load from the overloaded small cells to the macrocells in selective way. In some cases, the balance improvement ratio can reach 97.94%. Moreover, the overall balance efficiency is increased by 51.32% compared to the case without transferring users to the macrocells.","PeriodicalId":283197,"journal":{"name":"Proceedings of the 2nd International Conference on Telecommunications and Communication Engineering","volume":"258 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124240290","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}
M. J. M. Kiki, Zhang Jianbiao, Adolphe Bonzou Kouassi
Aiming at the iterative characteristics of the clustering process of fuzzy C-means clustering (CLUSTERING, FCM) algorithm, an iterative MapReduce model is used for FCM. The algorithm is optimized, the map function calculates the membership degree of each sample to the cluster center, the reduce function receives the new cluster center of the middle output of the map function, and the transfer module transmits the newest cluster center to the original map task node for the new round of mapreduce job; iterative The MapReduce model adds a transfer module to the MapReduce basic model, which effectively solves the deficiencies of the basic model in dealing with the iterative problem. In the Hadoop platform, we use FCM based on the iterative MapReduce and MapReduce basic models, respectively. The algorithm is used to diagnose the transformer; the experimental results show that the diagnostic speed of FCM algorithm based on iterative mapreduce is more than 12 times of the MapReduce basic model algorithm, the misjudgment rate is lower 12 to 15 percent, and the diagnostic efficiency of FCM algorithm is improved effectively.
{"title":"Improved Iteration FCM Algorithm for MapReduce Research","authors":"M. J. M. Kiki, Zhang Jianbiao, Adolphe Bonzou Kouassi","doi":"10.1145/3291842.3291889","DOIUrl":"https://doi.org/10.1145/3291842.3291889","url":null,"abstract":"Aiming at the iterative characteristics of the clustering process of fuzzy C-means clustering (CLUSTERING, FCM) algorithm, an iterative MapReduce model is used for FCM. The algorithm is optimized, the map function calculates the membership degree of each sample to the cluster center, the reduce function receives the new cluster center of the middle output of the map function, and the transfer module transmits the newest cluster center to the original map task node for the new round of mapreduce job; iterative The MapReduce model adds a transfer module to the MapReduce basic model, which effectively solves the deficiencies of the basic model in dealing with the iterative problem. In the Hadoop platform, we use FCM based on the iterative MapReduce and MapReduce basic models, respectively. The algorithm is used to diagnose the transformer; the experimental results show that the diagnostic speed of FCM algorithm based on iterative mapreduce is more than 12 times of the MapReduce basic model algorithm, the misjudgment rate is lower 12 to 15 percent, and the diagnostic efficiency of FCM algorithm is improved effectively.","PeriodicalId":283197,"journal":{"name":"Proceedings of the 2nd International Conference on Telecommunications and Communication Engineering","volume":"156 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121288375","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}
Based on the fractional Fourier transform (FrFT), the authors propose a novel method for multipath separation and measurement of root mean square (RMS) delay spread by using a chirp pilot symbols. Different multipath chirp components with different time delays will be concentrated on different fractional frequency points in fractional Fourier domain (FrFD) through FrFT. Meanwhile, the envelope amplitude of a concentrated component indicates the corresponding signal energy. Therefore, the different multipath components can be separated clearly and the RMS delay spread of a multipath channel can be measured accurately in FrFD.
{"title":"A Novel Method for Multipath Separation and Measurement of Root Mean Square Delay Spread Based on Fractional Fourier Transform in a Multipath Channel","authors":"Zeyi Yang, R. Tao, Yue Wang","doi":"10.1145/3291842.3291902","DOIUrl":"https://doi.org/10.1145/3291842.3291902","url":null,"abstract":"Based on the fractional Fourier transform (FrFT), the authors propose a novel method for multipath separation and measurement of root mean square (RMS) delay spread by using a chirp pilot symbols. Different multipath chirp components with different time delays will be concentrated on different fractional frequency points in fractional Fourier domain (FrFD) through FrFT. Meanwhile, the envelope amplitude of a concentrated component indicates the corresponding signal energy. Therefore, the different multipath components can be separated clearly and the RMS delay spread of a multipath channel can be measured accurately in FrFD.","PeriodicalId":283197,"journal":{"name":"Proceedings of the 2nd International Conference on Telecommunications and Communication Engineering","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123705923","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 Optimal Training Parameter Combination (OPTC) is the core of the support vector machines (SVM) to construct application model. However, the calculated amount of searching OTPC of SVM is extremely huge, which is time-consuming during the process of implementation by the software. To solve this issue, we propose a Shared Dot Product Matrix (SDPM) algorithm. The algorithm computes the dot product of all training data sets and stores them simultaneously, which achieves an ultra-fast processing speed. Meanwhile, the hardware/software co-design architecture for searching OTPC of SVM is proposed to corporate the data processing. The implementation and test results have shown that, the software and hardware collaboration system proposed in this paper has the performance that is 30 times faster in searching speed than software-based LIBSVM.
{"title":"Design and Implementation of Searching SVM Optimal Training Parameter Set Based on Shared Dot Product Matrix","authors":"Wei Cao, Shang Ma, Jianhao Hu, Luxi Lu","doi":"10.1145/3291842.3291897","DOIUrl":"https://doi.org/10.1145/3291842.3291897","url":null,"abstract":"The Optimal Training Parameter Combination (OPTC) is the core of the support vector machines (SVM) to construct application model. However, the calculated amount of searching OTPC of SVM is extremely huge, which is time-consuming during the process of implementation by the software. To solve this issue, we propose a Shared Dot Product Matrix (SDPM) algorithm. The algorithm computes the dot product of all training data sets and stores them simultaneously, which achieves an ultra-fast processing speed. Meanwhile, the hardware/software co-design architecture for searching OTPC of SVM is proposed to corporate the data processing. The implementation and test results have shown that, the software and hardware collaboration system proposed in this paper has the performance that is 30 times faster in searching speed than software-based LIBSVM.","PeriodicalId":283197,"journal":{"name":"Proceedings of the 2nd International Conference on Telecommunications and Communication Engineering","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128645873","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}
Based on the characteristics of dual-sided paralleled stripe in impedance tuning, the antenna was miniaturized by using the ACS feeding structure. A compact quad-band antenna was designed and implemented. The proposed antenna volume is about 50% smaller than the original design. The overall size is only 40mm × 15mm × 1.5mm. The resonant frequency of the proposed antenna is optimized and increased to four, which are 1.93GHz - 2.2GHz, 3.2GHz - 4.2GHz, 4.5GHz - 4.7GHz and 5.4GHz - 5.8GHz, respectively. The proposed antenna is suitable for 2.1/3.5GHz LTE, 5.8GHz WLAN and 3.5/4.5GHz 5G network application.
{"title":"Compact ACS-Fed Quad-Band Antenna for LTE/WLAN/5G Applications","authors":"Yang Yang, Yuan Liu, Fan Wu","doi":"10.1145/3291842.3291873","DOIUrl":"https://doi.org/10.1145/3291842.3291873","url":null,"abstract":"Based on the characteristics of dual-sided paralleled stripe in impedance tuning, the antenna was miniaturized by using the ACS feeding structure. A compact quad-band antenna was designed and implemented. The proposed antenna volume is about 50% smaller than the original design. The overall size is only 40mm × 15mm × 1.5mm. The resonant frequency of the proposed antenna is optimized and increased to four, which are 1.93GHz - 2.2GHz, 3.2GHz - 4.2GHz, 4.5GHz - 4.7GHz and 5.4GHz - 5.8GHz, respectively. The proposed antenna is suitable for 2.1/3.5GHz LTE, 5.8GHz WLAN and 3.5/4.5GHz 5G network application.","PeriodicalId":283197,"journal":{"name":"Proceedings of the 2nd International Conference on Telecommunications and Communication Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128838699","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Due to the large number of mobile applications (Apps) installed on the smartphones, it becomes time-consuming for the user to find the Apps he or she want to use, therefore, it is important to predict App usage based on understanding of mobile user's behavior. In this paper, we use mobile Internet traffic data to construct User-App bipartite network, and transform the App usage prediction task to a link prediction problem. To better mine the relations between users and Apps, we propose a new node based and two path based similarities that are bidirectional conditional probability (BCP) similarity based on preference property of nodes, local shortest path (LSP) similarity based on closeness relationship between nodes, and random walk with resource redistribution (RWRR) similarity based on the node degree. We propose an App usage prediction framework BLR-AUP to predict which App the user will use. Experiment results showed that our model outperformed other traditional link prediction models, with high F1 and AUC value of 91.14% and 96.43%.
{"title":"Predicting App Usage from Mobile Internet Traffic Data Based on Node and Path Similarity","authors":"Hui Chen, K. Yu, Xiaofei Wu","doi":"10.1145/3291842.3291909","DOIUrl":"https://doi.org/10.1145/3291842.3291909","url":null,"abstract":"Due to the large number of mobile applications (Apps) installed on the smartphones, it becomes time-consuming for the user to find the Apps he or she want to use, therefore, it is important to predict App usage based on understanding of mobile user's behavior. In this paper, we use mobile Internet traffic data to construct User-App bipartite network, and transform the App usage prediction task to a link prediction problem. To better mine the relations between users and Apps, we propose a new node based and two path based similarities that are bidirectional conditional probability (BCP) similarity based on preference property of nodes, local shortest path (LSP) similarity based on closeness relationship between nodes, and random walk with resource redistribution (RWRR) similarity based on the node degree. We propose an App usage prediction framework BLR-AUP to predict which App the user will use. Experiment results showed that our model outperformed other traditional link prediction models, with high F1 and AUC value of 91.14% and 96.43%.","PeriodicalId":283197,"journal":{"name":"Proceedings of the 2nd International Conference on Telecommunications and Communication Engineering","volume":"197 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125862116","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：