2019 IEEE 5th International Conference on Computer and Communications (ICCC)最新文献_第5页

Pilot Allocation Algorithm Based on User Grouping in Massive MIMO Systems 大规模MIMO系统中基于用户分组的导频分配算法

2019 IEEE 5th International Conference on Computer and Communications (ICCC) Pub Date : 2019-12-01 DOI: 10.1109/ICCC47050.2019.9064195

K. Qian, Feng Wenjiang

{"title":"Pilot Allocation Algorithm Based on User Grouping in Massive MIMO Systems","authors":"K. Qian, Feng Wenjiang","doi":"10.1109/ICCC47050.2019.9064195","DOIUrl":"https://doi.org/10.1109/ICCC47050.2019.9064195","url":null,"abstract":"In order to improve the accuracy of the pilot-aided channel estimation in massive multiple-input multiple-output (MIMO) systems, a user grouping based pilot allocation algorithm (UGPA) is proposed according to the large-scale fading coefficient. The users are divided into the cell-edge and the cell-center groups, whereby the edge users apply for the orthogonal pilot that cannot reused in all cells. On the contrast, the center users apply for the pilot which can be reused by other cell user. Alternatively, the cell-center users are sorted in ascending order by the polar angles, and the pilot sequences are sequentially allocated. That ensures a large spacing between the central users who select the same pilot. Furthermore, in order to decrease the pilot overhead, an improved user grouping based pilot allocation algorithm (IUGPA) is proposed based on the UGPA, which joints the user location information. To begin with, the user grouping is performed according to the user’s uplink channel large-scale fading. Then, the cell-edge users are selected a second division based on the space distance between the user and base station, and the same pilot allocation strategy as the UGPA is adopted. The simulation results demonstrated that the IUGPA algorithm significantly reduce the pilot overhead compared with the soft pilot reuse (SPR) algorithm. Moreover, the uplink sum achievable rate is boosted with the UGPA algorithm and the IUGPA algorithm at different degrees.","PeriodicalId":6739,"journal":{"name":"2019 IEEE 5th International Conference on Computer and Communications (ICCC)","volume":"2 1","pages":"1120-1125"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81062925","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}

引用次数: 1

Attention-Based User Temporal Model for Recommendation 基于注意力的用户推荐时间模型

2019 IEEE 5th International Conference on Computer and Communications (ICCC) Pub Date : 2019-12-01 DOI: 10.1109/ICCC47050.2019.9064186

Xinrui Yuan, Cheng Yang

引用次数: 1

Design of Charging Power Supply Management System for Electric Toys 电动玩具充电电源管理系统的设计

2019 IEEE 5th International Conference on Computer and Communications (ICCC) Pub Date : 2019-12-01 DOI: 10.1109/ICCC47050.2019.9064431

Li Guangxu, Liu Guangqian, L. Qin

引用次数: 0

An LSTM Acceleration Engine for FPGAs Based on Caffe Framework 基于Caffe框架的fpga LSTM加速引擎

2019 IEEE 5th International Conference on Computer and Communications (ICCC) Pub Date : 2019-12-01 DOI: 10.1109/ICCC47050.2019.9064358

Junhua He, Dazhong He, Yang Yang, Jun Liu, Jie Yang, Siye Wang

{"title":"An LSTM Acceleration Engine for FPGAs Based on Caffe Framework","authors":"Junhua He, Dazhong He, Yang Yang, Jun Liu, Jie Yang, Siye Wang","doi":"10.1109/ICCC47050.2019.9064358","DOIUrl":"https://doi.org/10.1109/ICCC47050.2019.9064358","url":null,"abstract":"Recently, Long Short Term Memory (LSTM) networks have been widely used in sequence-related problem. LSTMs outperform conventional feed-forward neural networks and RNNs in many ways, since they remember patterns selectively for long durations of time. However, due to the recurrent property of LSTMs, it is hard to implement a high computing parallelism on general processors such as CPUs and GPUs. Besides, the huge energy consumption of GPU and CPU computing is a non-negligible issue for data centers. In order to solve the problems above, FPGA emerges as an ideal solution. It has the characteristics of low power and latency, which has natural advantages for the implementation of recurrent neural networks, such as LSTMs. In this paper, we propose to implement an acceleration engine for LSTM network based on FPGAs. By employing fixed-point arithmetic, systolic arrays for matrix multiplication and look up table for activate function, we optimize the LSTM on FPGA in depth. Additionally, we integrate the acceleration engine into Caffe, one of the most popular deep learning framework, to make it easier to deploy. According to the experimental results, our acceleration engine achieves 8.8X and 2.2X gains for performance, 16.9X and 9.6X gains for energy efficiency compared with CPU and GPU, respectively.","PeriodicalId":6739,"journal":{"name":"2019 IEEE 5th International Conference on Computer and Communications (ICCC)","volume":"49 1","pages":"1286-1292"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88618820","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}

引用次数: 2

Learning Path Recommendation Based on Knowledge Tracing Model and Reinforcement Learning 基于知识跟踪模型和强化学习的学习路径推荐

2019 IEEE 5th International Conference on Computer and Communications (ICCC) Pub Date : 2019-12-01 DOI: 10.1109/ICCC47050.2019.9064104

Dejun Cai, Yuan Zhang, B. Dai

引用次数: 14

C4.5 Algorithm Based on the Sample Selection and Cosine Similarity 基于样本选择和余弦相似度的C4.5算法

2019 IEEE 5th International Conference on Computer and Communications (ICCC) Pub Date : 2019-12-01 DOI: 10.1109/ICCC47050.2019.9064346

Suzhi Zhang, Xiao-Ni Chen

{"title":"C4.5 Algorithm Based on the Sample Selection and Cosine Similarity","authors":"Suzhi Zhang, Xiao-Ni Chen","doi":"10.1109/ICCC47050.2019.9064346","DOIUrl":"https://doi.org/10.1109/ICCC47050.2019.9064346","url":null,"abstract":"In order to improve the accuracy of classification, shorten the training time of high-dimensional large sample set, and reduce the redundancy rules of decision tree, a C4.5 improved algorithm based on the sample selection and cosine similarity is proposed. Processing large sample set, the algorithm first uses the statistics optimum sample size algorithm to determine the optimum sample size of data set. Then, the optimal size samples are selected from the data set, the accuracy of the selected training samples is highly optimized as iterative information, and an optimal training set is found from the iterative process. After, according to the difference between any two attribute information entropies in the training sample, the potential similarity attribute is searched, the cosine similarity of the potential similar attribute pairs is calculated, the attributes with the similarity within the threshold range are combined, and the information gain rate of the merged attribute is calculated. Finally on the basis of the traditional C4.5 algorithm to choose the best split attribute, build a decision tree. The simulation results show that the proposed algorithm is compared with the traditional C4.5 algorithm, to reduce the redundant rules, improves the execution efficiency and classification accuracy.","PeriodicalId":6739,"journal":{"name":"2019 IEEE 5th International Conference on Computer and Communications (ICCC)","volume":"29 1","pages":"490-495"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83626506","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}

引用次数: 0

A New Designed MIMO-NOMA Scheme for HSR System with Distributed Antennas 高铁分布式天线MIMO-NOMA新方案设计

2019 IEEE 5th International Conference on Computer and Communications (ICCC) Pub Date : 2019-12-01 DOI: 10.1109/ICCC47050.2019.9064479

Zecheng Zhang, Yang Liu

{"title":"A New Designed MIMO-NOMA Scheme for HSR System with Distributed Antennas","authors":"Zecheng Zhang, Yang Liu","doi":"10.1109/ICCC47050.2019.9064479","DOIUrl":"https://doi.org/10.1109/ICCC47050.2019.9064479","url":null,"abstract":"This paper investigates the MIMO-NOMA transmission scheme for high-speed railway (HSR). To the best of our knowledge, this is the first work that attempts to implement NOMA principle into HSR wireless system. Attracted by the technological superiority of distributed antenna system (DAS) and MIMO-NOMA, we propose a new transmission scheme and compare it with the conventional transmission strategy. We treat each antenna unit of the distributed antenna system as an independent user, group these users at each time slot, and apply NOMA principles within each group. We adopt a simple method to ensure that users with large channel state differences are grouped into the same cluster, and introduce average service rate to measure the system performance. At the same time, we have discussed the effect of fixed power allocation and dynamic power allocation on the system transmission rate within MIMONOMA and MIMO-OMA. The simulation results illustrate that the dynamic power allocation scheme is superior to the fixed power allocation, and the MIMO-NOMA system we proposed is always superior to the conventional MIMO-OMA scheme in high speed railways.","PeriodicalId":6739,"journal":{"name":"2019 IEEE 5th International Conference on Computer and Communications (ICCC)","volume":"26 1","pages":"690-695"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86585437","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}

引用次数: 0

In Situ Caching using Combined TTL-FIFO Algorithm 结合TTL-FIFO算法的原位缓存

2019 IEEE 5th International Conference on Computer and Communications (ICCC) Pub Date : 2019-12-01 DOI: 10.1109/ICCC47050.2019.9064459

Gasydech Lergchinnaboot, Peraphon Sophatsathit, Saranya Maneeroj

引用次数: 3

A Fuzzy Rule-Based Krill Herd Algorithm 基于模糊规则的磷虾群算法

2019 IEEE 5th International Conference on Computer and Communications (ICCC) Pub Date : 2019-12-01 DOI: 10.1109/ICCC47050.2019.9064372

Fang Su, Wenzhe Yang, C. Duan, Jilong Li

引用次数: 0

Bi-Transfer: A Data Packet Allocation Module with Chaining Transmission Mode 双传输:采用链式传输方式的数据包分配模块

2019 IEEE 5th International Conference on Computer and Communications (ICCC) Pub Date : 2019-12-01 DOI: 10.1109/ICCC47050.2019.9064474

Zerun Li, Sen Yang, Yu Wang, Lirui Chen, Yang Guo, Zuocheng Xing

{"title":"Bi-Transfer: A Data Packet Allocation Module with Chaining Transmission Mode","authors":"Zerun Li, Sen Yang, Yu Wang, Lirui Chen, Yang Guo, Zuocheng Xing","doi":"10.1109/ICCC47050.2019.9064474","DOIUrl":"https://doi.org/10.1109/ICCC47050.2019.9064474","url":null,"abstract":"With the increasing performance requirements of network data interaction on chip, the traditional Direct Memory Access (DMA) often performs with low efficiency of multi-module collaboration due to the competition of bus control, thereby reducing the throughput rate of the bus. Aiming at the working characteristics of inter-core communication and data interaction between multiple modules, this paper designs a packet transmission module Bi-Transfer that supports bidirectional data flow between multiple modules It also realizes chaining transmission of input and output data in parallel with various configuration modes and flexible data scheduling modes. This module can complete the functions of data movement, inter-core communication, task management, etc., and use descriptors to link load data packets to uniformly conFigure the data interaction mode of the on-chip network. In the experimental stage, function planning and code design are carried out first, then the timing simulation and data recording are described. Finally, the performance characteristics of this new data interaction module are discussed. According to statistical observations, increasing the number of channels in the design module can significantly increase the bandwidth of the bus. Under the given clock frequency, bus width and data transmission requirements, the bus operating bandwidth in the four-channel working mode can reach up to 4690 MB/s at most, which is nearly 400 MB/s beyond the ordinary DMA bus bandwidth. In the case of fewer channels, this module can fulfill the data scheduling requirements of most applications and provide the data moving function of ordinary DMA.","PeriodicalId":6739,"journal":{"name":"2019 IEEE 5th International Conference on Computer and Communications (ICCC)","volume":"71 1","pages":"473-478"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89940500","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}

引用次数: 0