2022 7th International Conference on Computer and Communication Systems (ICCCS)最新文献

{"title":"Self-Supervised Image Aesthetic Assessment Inspired by Aesthetic Domain Knowledge","authors":"Qiong Li","doi":"10.1109/icccs55155.2022.9846053","DOIUrl":"https://doi.org/10.1109/icccs55155.2022.9846053","url":null,"abstract":"Photographic rules describe how to create high-quality images by imposing restrictions on some aspects like lighting and color. Such rules referred to as domain knowledge, turn out to be crucial in enhancing the performance of image aesthetic assessment. Although many research efforts have been made, aesthetic domain knowledge is underutilized, and a large amount of labeled data are typically required. To remedy these issues, we propose an improved multi-task self-supervised method under the guidance of aesthetic domain knowledge. In the pre-training phase, we design multiple pretext tasks for a naïve network to predict the levels of the properties related to photographic rules. That enables the network to learn visual features sensitive to image aesthetic information. After that, the well-trained network is applied to evaluate the aesthetic quality of images. Experiments on two benchmark datasets elucidate that the features learned by the network can discern aesthetic images according to their difference in photographic properties. The promising results demonstrate that the proposed method can successfully leverage aesthetic domain knowledge to learn effective features from large-scale unlabeled data for image aesthetic assessment.","PeriodicalId":121713,"journal":{"name":"2022 7th International Conference on Computer and Communication Systems (ICCCS)","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131814709","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}

{"title":"Design of End-to-end Service Orchestrator System for Multi-technology Networks","authors":"Yanlei Zheng, Guangquan Wang, Yacheng Liu","doi":"10.1109/icccs55155.2022.9846086","DOIUrl":"https://doi.org/10.1109/icccs55155.2022.9846086","url":null,"abstract":"In the carrier’s dedicated line market, the end-to-end service orchestrator system for multi-technology networks is becoming increasingly significant. The functionalities and software infrastructure designs of China Unicom’s E2E service orchestrator system for multi-technology networks are described in this paper. On a unique method, this system uses the controller-on-demand path-calculation mode to achieve rapid service delivery in a flat SDN architecture. The paper also discusses the principal important technologies that were employed in the system development process.","PeriodicalId":121713,"journal":{"name":"2022 7th International Conference on Computer and Communication Systems (ICCCS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133150925","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}

{"title":"An FPGA-Based Identifier Mapping Module Design for Space-Air-Ground Integrated Network","authors":"Y. Chao, Hongchao Wang, Yuhong Xiang, Hongke Zhang","doi":"10.1109/icccs55155.2022.9846038","DOIUrl":"https://doi.org/10.1109/icccs55155.2022.9846038","url":null,"abstract":"In the space-air-ground integrated network (SAGIN) based on identifier mapping protocol (IDP), IDP separates user space and network space apart, which is difficult for traditional networks to accomplish. The communication quality and topology between satellites change rapidly in the actual environment, so high-quality satellite communication requires satellite nodes to process data packets with a lower delay. However, the previous software-based implementation scheme is limited by Von Neumann Architecture, which is hard to greatly reduce the processing delay. Not all the content in the IDP stack needs to be processed flexibly, so that FPGA can be used for accelerating the parts with high locality and repetitiveness. To provide lower latency for identifier mapping in future deployment, this paper proposes an FPGA-based identifier mapping module design, which hardwareizes the mapping process and demapping process between IP address and the routing identifier (RID) in the identifier switch router (IDSR) deployed on the satellite. Meanwhile, to further shorten the average processing delay, this design adopts Least-Recently-Used (LRU) algorithm for optimization. This paper describes the framework of the design in detail, and the experiment results in the emulation environment prove that the mapping processing delay of the FPGA-based identifier mapping module design is able to provide a lower delay for IDSR in SAGIN.","PeriodicalId":121713,"journal":{"name":"2022 7th International Conference on Computer and Communication Systems (ICCCS)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134099200","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}

{"title":"Highly Portable C++ Based Simulator with Dual Parallelism and Spatial Decomposition of Simulation Domain using Floating Point Operations and More Flops Per Watt for Better Time-To-Solution on Particle Simulation","authors":"Nisha Agrawal, A. Das, R. Pathak, M. Modani","doi":"10.1109/icccs55155.2022.9846280","DOIUrl":"https://doi.org/10.1109/icccs55155.2022.9846280","url":null,"abstract":"LAMMPS is a classical molecular dynamics (MD) code that models ensembles of particles in a solid, liquid, or gaseous state. LAMMPS performance has been optimized over the years. This paper focuses on the study of MD simulations using LAMMPS on the PARAM Siddhi-AI system. LAMMPS’s performance is analyzed with the number of the latest NVIDIA A100 co-processor (GPU) based on Ampere architecture. The faster and larger L1 cache and shared memory in Ampere architecture (192 KB per Streaming Multiprocessor (SM)) delivers additional speedups for High-Performance Computing (HPC) workloads. In this work, single-node multi-GPUs as well as multi-node multi-GPUs (up to 5 nodes) LAMMPS performance for two input datasets LJ 2.5 (intermolecular pair potential) and EAM (interatomic potential), on PARAM Siddhi-AI system, is discussed. Performance improvement of GPU-enabled LAMMPS run over CPU-only performance is demonstrated for both the inputs data sets. LAMMPS performance is analyzed for initialization, atoms communication, forces, thermodynamic state (Pair (non-bonded force computations), Neigh (neighbor list construction), Comm (inter-processor communication of atoms and their properties), Output (output of thermodynamic info and dump files), Modify (fixes and computes invoked by fixes) and others (all the remaining time forces and functions)). GPU utilization (in terms of computing and memory) is also discussed for both the input datasets. GPU enabled LAMMPS single-node performance shows 31x and 125x speed-up in comparison to single-node CPU-only performance for LJ2.5 and EAM input datasets respectively. LAMMPS scales well across multi-node and shows almost linear scalability. In comparison to single node GPU enabled LAMMPS run, the observed speedup is 4.1x and 3.8x on 5 nodes, for LJ2.5 and EAM input datasets respectively. LAMMPS performance comparison across GPU generation shows 1.5x to 1.9x speedup on A100 GPUs over V100 GPUs.","PeriodicalId":121713,"journal":{"name":"2022 7th International Conference on Computer and Communication Systems (ICCCS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134399119","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}

{"title":"The Study of Marine Intelligent Antenna Technology Based on Beamforming Algorithm","authors":"Peng Liu, Yizheng Wu, Han Xiao, Ying Chen","doi":"10.1109/icccs55155.2022.9846088","DOIUrl":"https://doi.org/10.1109/icccs55155.2022.9846088","url":null,"abstract":"Maritime communication system is an important part of real-time battlefield information transmission. In this paper, adaptive smart antenna beamforming technology is applied to maritime communication, and a one-dimensional antenna array structure model and signal model are proposed. At the same time, the adaptive beamforming algorithm in smart antenna is studied. Since the classical LMS beamforming algorithm has slow convergence speed and poor adaptability, genetic algorithm is applied to array antenna beamforming in this paper. And the traditional genetic algorithm is optimized and improved in initial population planning and crossover operation. The simulation results show that compared with LMS algorithm, traditional genetic algorithm and the optimized genetic algorithm has better convergence effect of mean square error, more accurate suppression of interference signal by beamforming, better practicability and development potential.","PeriodicalId":121713,"journal":{"name":"2022 7th International Conference on Computer and Communication Systems (ICCCS)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132441765","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}

{"title":"Temporal Factorized Bilinear Modules with 2D CNN for Action Recognition in Videos","authors":"Jue Wang, Huanzhang Lu, Yao Zhang, Feng Ma, Moufa Hu","doi":"10.1109/icccs55155.2022.9846526","DOIUrl":"https://doi.org/10.1109/icccs55155.2022.9846526","url":null,"abstract":"Action recognition is to automatically detect and classify human’s action in videos, with difficulty lies in modeling temporal relationship between frame sequences. The well-used 2D convolution neural network (CNN) is not suitable for this work, due to lacking temporal modeling ability. In this paper, a novel 2D CNN with inter frame information extraction module based on bilinear operation is proposed to deal with this problem. This model can greatly improve the temporal modeling ability of 2D CNN and just introduce a small amount of storage and calculation via parameter decomposition method. In addition, it has a flexible form to easily make tradeoff between performance and complexity. Finally, the effectiveness of this new network is validated on two kinds of benchmarks including both temporal-related (Something-Something v1) and scene-related(mini-kinetics), with top-1 accuracy 44.5% and 67.8% respectively, which reach or exceed the performance of existing methods with the similar model complexity.","PeriodicalId":121713,"journal":{"name":"2022 7th International Conference on Computer and Communication Systems (ICCCS)","volume":"331 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133875639","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}

{"title":"Oriented-YOLOv5: A Real-time Oriented Detector Based on YOLOv5","authors":"X. Li, Zhenhua Cai, Xi Zhao","doi":"10.1109/icccs55155.2022.9846234","DOIUrl":"https://doi.org/10.1109/icccs55155.2022.9846234","url":null,"abstract":"Current state-of-the-art oriented detectors have time-consuming feature extraction backbones, oriented proposals generation methods or additional special branches. These tricks increase the computational cost of oriented detectors and prevent them from some practical applications. YOLOv5 is one of the best real-time (inference time⩽33.3ms, or FPS⩾30) detectors in the field of general target detection that can be applied in various real tasks. However, YOLOv5 does not output the angular prediction that is crucial to reflect attitudes and shapes of the targets. We propose Oriented-YOLOv5 that can output angular prediction of rotated target and achieve real-time detection in aerial images. Specifically, we integrate Circular Smooth Label (CSL) into YOLOv5 (v5.0), so it inherits both the fast and lightweight features of YOLOv5 and the high performance of CSL for angle detection. Experimental results indicate that Oriented-YOLOv5s achieves an accuracy of 68.24% mAP and an efficiency of 11.8ms with aerial images of 1024×1024 input size. It can be further improved (68.86% mAP and 10.8ms) using Conv instead of Focus. We also integrate CSL into YOLOv5m and YOLOv5l, and they achieve improved accuracies (70.03% mAP and 71.2% mAP, respectively) and retain real-time inference speed. Overall, Oriented-YOLOv5 is well suited for detection tasks that have vertical view and require angular prediction with highly real-time and limited memory, so it can be used for applications deployed to satellites, UAVs, or robotic arms. Source code: https://github.com/Leesanjin/Oriented-YOLOv5","PeriodicalId":121713,"journal":{"name":"2022 7th International Conference on Computer and Communication Systems (ICCCS)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132916757","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}

{"title":"Compact High Isolation CPW Fed 4-Element UWB-MIMO Antenna with Special Isolation Structure","authors":"Xianbiao Zha, Chunhua Li, Shaoxian Chen, Wenfei Yin, Xiaohui Zhang","doi":"10.1109/icccs55155.2022.9846083","DOIUrl":"https://doi.org/10.1109/icccs55155.2022.9846083","url":null,"abstract":"This paper proposes a four-element ultra-wideband MIMO antenna. The antenna is composed of four half-cut monopole sub-elements, which are placed perpendicular to each other, adopting an improved CPW feeding method, and adding a special isolation structure to achieve high isolation. Combined with the new structure of the semi-circumferential ground, the impedance matching in the ultra-wideband range is realized. With many improvements and optimizations, excellent antenna performance has been achieved. Both simulation and test results show that the designed antenna working bandwidth can cover the 2.71-19.70GHz frequency band, the isolation within the entire bandwidth is greater than 18dB, the antenna’s radiation omnidirectionality is good, the radiation efficiency reaches more than 73%, and it has good gain characteristics, Envelope Correlation Coefficient (ECC) shows that the antenna can well meet the polarization diversity characteristics, the antenna has a compact overall size of only 38*38*1.6mm3. The antenna we designed can be used for portable wireless ultra-wideband applications.","PeriodicalId":121713,"journal":{"name":"2022 7th International Conference on Computer and Communication Systems (ICCCS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133927977","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}

{"title":"Research on Target Grouping Method Based on Graph Neural Network","authors":"Yang Zhang, Peng-fei Peng, Rui Lu","doi":"10.1109/icccs55155.2022.9846007","DOIUrl":"https://doi.org/10.1109/icccs55155.2022.9846007","url":null,"abstract":"With the application of a large number of battlefield observation sensors, the battlefield target data obtained by the command and control system has shown a surge trend. The scale of target information data is large, problems such as high dimensionality and complex structure have brought new challenges to the target grouping technology. The traditional clustering method has been unable to effectively target grouping in high-dimensional battlefield target data. Aiming at the dilemma of current target grouping technology, in order to help commanders get different types of target groups, this paper constructs a target grouping algorithm based on graph neural network, which combines graph convolutional neural network and clustering algorithm, and uses self-supervised mechanism to optimize the model. Through the verification experiment of the target clustering model on 4 high-dimensional data sets, three clustering effect evaluation indicators are established, and compared with the two methods of K-means and AE+k-means, it proves that our method is more efficient and intelligent.","PeriodicalId":121713,"journal":{"name":"2022 7th International Conference on Computer and Communication Systems (ICCCS)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115710013","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}

{"title":"Design of a Current-Controlled Microwave Power Attenuator with Large Attenuation","authors":"S. Shan","doi":"10.1109/icccs55155.2022.9846366","DOIUrl":"https://doi.org/10.1109/icccs55155.2022.9846366","url":null,"abstract":"PIN diodes are widely used in the microwave field. According to their characteristics, this paper deduces the use of PIN diodes as current-controlled attenuators through formula derivation, and achieves good results that high attenuation can be precisely controlled.","PeriodicalId":121713,"journal":{"name":"2022 7th International Conference on Computer and Communication Systems (ICCCS)","volume":"411 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116518639","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}