发布求助
文献互助 智能选刊 最新文献

Proceedings of the 5th International Conference on Computer Science and Application Engineering最新文献

筛选
英文 中文
A TCP Congestion Control Algorithm Based on Deep Reinforcement Learning Combined with Probe Bandwidth Mechanism 基于深度强化学习和探测带宽机制的TCP拥塞控制算法
Proceedings of the 5th International Conference on Computer Science and Application Engineering Pub Date : 2021-10-19 DOI: 10.1145/3487075.3487119
Mengting Li, Xiang Huang, Chengyang Jin, Yijian Pei
{"title":"A TCP Congestion Control Algorithm Based on Deep Reinforcement Learning Combined with Probe Bandwidth Mechanism","authors":"Mengting Li, Xiang Huang, Chengyang Jin, Yijian Pei","doi":"10.1145/3487075.3487119","DOIUrl":"https://doi.org/10.1145/3487075.3487119","url":null,"abstract":"The rapid development of emerging Internet services such as live video, 5G, VR, and the Internet of Things puts forward higher requirements for network throughput, Latency, jitter, and loss. However, the inefficient bandwidth utilization rate of the existing TCP protocol cannot meet these requirements. Based on this problem, this paper proposes an algorithm RL-explore that uses RL (Reinforcement learning) combined with bandwidth detection mechanism. The model trained with this algorithm can effectively use the network bandwidth, and compared to other RL algorithms, it is easier to converge during training.","PeriodicalId":354966,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Application Engineering","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127368762","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
Towards Formal Verification of Dynamic Memory Allocator Properties Using BIP Framework 基于BIP框架的动态内存分配器属性形式化验证
Proceedings of the 5th International Conference on Computer Science and Application Engineering Pub Date : 2021-10-19 DOI: 10.1145/3487075.3487122
Xiutai Lu, Yang Gao, Wensheng Guo, F. Zhang, Xia Yang, Jun Wan
{"title":"Towards Formal Verification of Dynamic Memory Allocator Properties Using BIP Framework","authors":"Xiutai Lu, Yang Gao, Wensheng Guo, F. Zhang, Xia Yang, Jun Wan","doi":"10.1145/3487075.3487122","DOIUrl":"https://doi.org/10.1145/3487075.3487122","url":null,"abstract":"Dynamic storage allocation (DSA) algorithms play an important role in the Real-Time Operating systems (RTOSs) community. It allows the RTOS to use limited memory efficiently. To ensure the DSA properties of a dynamic memory allocator, it is important to verify the implementation of its DSA algorithms. However, most previous works ignore memory interactive behaviors and just verify individually each function involved in DSA. Our main contribution in this paper is to verify the consistency of the memory interactive properties and its implementation. For this purpose, we use the BIP (Behavior, Interaction, Priority) Framework to deal with abstract behaviors, properties, and cross references to implementation code. We chose the TLSF as a testbed for formal verification of dynamic memory allocator properties and have produced a verification of TLSF. Both the behavior operations and property requirements of the TLSF have been specified in the BIP framework and the entire verification process is automated.","PeriodicalId":354966,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Application Engineering","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127528425","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
Improved Pedestrian Detection Algorithm of Yolov4 Network Structure 改进的Yolov4网络结构行人检测算法
Proceedings of the 5th International Conference on Computer Science and Application Engineering Pub Date : 2021-10-19 DOI: 10.1145/3487075.3487088
Xiujun Zhu, Yujie Bai, Yijian Pei
{"title":"Improved Pedestrian Detection Algorithm of Yolov4 Network Structure","authors":"Xiujun Zhu, Yujie Bai, Yijian Pei","doi":"10.1145/3487075.3487088","DOIUrl":"https://doi.org/10.1145/3487075.3487088","url":null,"abstract":"When the YOLOV4 network detects pedestrians alone, the small target pedestrians will be missed, resulting in the reduction of P (Precision) and AP (Average Precision) values. This paper improves the YOLOV4 network structure. In order to improve the feature extraction capability of the network for small targets, a shallower feature layer is added to the original three output feature layers of the YOLOV4 backbone network to build PANet (Path Aggregation Network) together. And two SPP (Spatial Pyramid Pooling) structures are added to expand the receptive field. The channel attention mechanism module is added and some convolutional layers of the original network are deleted. Finally, transfer learning is used to make the detection effect better. The P value of the pedestrian on the PASCAL VOC data set increased from 84.43% to 91.37%, and the AP value increased from 74.78% to 87.39%, and the P value on the commonly used pedestrian detection data set INRIA (INRIA Person Dataset) increased from 93.20% increased to 98.02%, AP value increased from 91.08% to 94.02%. Experimental results show that the network has a better effect on pedestrian detection, and the accuracy and average precision are improved.","PeriodicalId":354966,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Application Engineering","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125095592","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 Semi-Supervised Railway Foreign Object Detection Method Based on GAN 基于GAN的半监督铁路异物检测方法
Proceedings of the 5th International Conference on Computer Science and Application Engineering Pub Date : 2021-10-19 DOI: 10.1145/3487075.3487133
Yanqi Chen, Shuzhen Tong, Xiaobo Lu, Yun Wei
{"title":"A Semi-Supervised Railway Foreign Object Detection Method Based on GAN","authors":"Yanqi Chen, Shuzhen Tong, Xiaobo Lu, Yun Wei","doi":"10.1145/3487075.3487133","DOIUrl":"https://doi.org/10.1145/3487075.3487133","url":null,"abstract":"The rapid development of deep learning provides new technical means for railway foreign object detection. However, in practical applications, the datasets of railways with foreign objects are scarce. In order to solve this problem, by improving the loss function and anomaly image evaluation standard, this paper proposes a new semi-supervised anomaly detection method based on GAN (Generative Adversarial Networks). Experiments show that our method can achieve railway foreign object detection without anomaly prior knowledge. Regarding anomaly recognition, a 0.058 AUC (Area Under Curve) and a 6% classification accuracy relative improvement for the railway dataset used in this paper are obtained.","PeriodicalId":354966,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Application Engineering","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121956823","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
Text Pared into Scene Graph for Diverse Image Generation 文本分割成场景图用于不同图像的生成
Proceedings of the 5th International Conference on Computer Science and Application Engineering Pub Date : 2021-10-19 DOI: 10.1145/3487075.3487158
Yonghua Zhu, Jieyu Huang, Ning Ge, Yunwen Zhu, Binghui Zheng, Wenjun Zhang
{"title":"Text Pared into Scene Graph for Diverse Image Generation","authors":"Yonghua Zhu, Jieyu Huang, Ning Ge, Yunwen Zhu, Binghui Zheng, Wenjun Zhang","doi":"10.1145/3487075.3487158","DOIUrl":"https://doi.org/10.1145/3487075.3487158","url":null,"abstract":"Although significant recent advances in condition generative model have shown remarkable improvements for controlled image generation, the image generation for multiple complex objects is still a challenge. To address the challenge, we propose a module of text description parsed into scene graph, which can generate reasonable scene layout to ensure the generated image and object realistic. Our proposed method enhances the interaction between objects and global semantics by concatenates each object embedding with text embedding To preserve the local image semantics, the Spatially-adaptive normalization(SPADE) layer is added into the generator of our model. We validate our method on Visual Genome and COCO-Stuff, where qualitative results and ablation study demonstrate the ability of our model in generating images with multiple objects and complex relationships.","PeriodicalId":354966,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Application Engineering","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129112755","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
A Two-step Model for Multi-object Tracking 多目标跟踪的两步模型
Proceedings of the 5th International Conference on Computer Science and Application Engineering Pub Date : 2021-10-19 DOI: 10.1145/3487075.3487083
Shuai Zhang, Xiaobo Lu, Songlin Du
{"title":"A Two-step Model for Multi-object Tracking","authors":"Shuai Zhang, Xiaobo Lu, Songlin Du","doi":"10.1145/3487075.3487083","DOIUrl":"https://doi.org/10.1145/3487075.3487083","url":null,"abstract":"Multi-object tracking is widely used in video analysis. However, due to the limitation of detector performance, many multi-object tracking models have the problem of detecting two objects into one object in some occlusion scenes. In this paper, we propose a two-step model for handling this problem. In the first step model, the non-occlusion targets are detected and embeddings are extracted, while the occlusion areas are identified. The second step model processes the occlusion areas to obtain occlusion targets' accurate positions and embeddings. Finally, we integrate and optimize the output results of the two steps models. Experiments show that the number of false positives and missed positives in our model's object detection is significantly reduced. The multi-object tracking performance (MOTA metric) is improved by nearly 3% compared with other models.","PeriodicalId":354966,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Application Engineering","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123978560","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
Research on High Performance Transmission Technology of DC Based on Network Awareness 基于网络感知的数据中心高性能传输技术研究
Proceedings of the 5th International Conference on Computer Science and Application Engineering Pub Date : 2021-10-19 DOI: 10.1145/3487075.3487153
Yanwei Wang, Cheng Huang, J. Fan, Le Yang, Hongwei Kan, Gaoming Cao
{"title":"Research on High Performance Transmission Technology of DC Based on Network Awareness","authors":"Yanwei Wang, Cheng Huang, J. Fan, Le Yang, Hongwei Kan, Gaoming Cao","doi":"10.1145/3487075.3487153","DOIUrl":"https://doi.org/10.1145/3487075.3487153","url":null,"abstract":"In recent years, RDMA over Converged Ethernet (RoCE) provides high performance data transmission for Data center (DC). RoCE has excellent performance in lossless network, but when the network environment is unstable, the transmission performance of RoCE will decline rapidly. This paper proposes a DC network transmission technology based on network awareness. By monitoring the network status, the network status can be updated in real time. The transmission mechanism can be adjusted dynamically. In order to support the transmission in harsh environment, this paper constructs DC-TCP transmission based on Data Plane Development Kit (DPDK) TCP and DC-RoCE transmission based on RoCE, and designs a high-performance DC-TCP / DC-RoCE fusion technology framework. The simulation results show that the DC network transmission technology based on network awareness significantly improves the transmission capacity of the DC in complex environment.","PeriodicalId":354966,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Application Engineering","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123985390","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
The System Adaptability Evaluation Index System of Military Communication Equipment System 军用通信装备系统适应性评价指标体系
Proceedings of the 5th International Conference on Computer Science and Application Engineering Pub Date : 2021-10-19 DOI: 10.1145/3487075.3487079
Jian Hou, Ruihua Wang, Jiajia Wang, Zhou Yang, Danyu He
{"title":"The System Adaptability Evaluation Index System of Military Communication Equipment System","authors":"Jian Hou, Ruihua Wang, Jiajia Wang, Zhou Yang, Danyu He","doi":"10.1145/3487075.3487079","DOIUrl":"https://doi.org/10.1145/3487075.3487079","url":null,"abstract":"As an objective reflection of equipment combat performance and battlefield satisfaction, the equipment combat test evaluation index system is the premise and basis for equipment combat test planning, design and implementation. It is to assess the system integration ability and matching ability of military communication equipment under actual combat conditions and the ability to join the equipment system for operation and training. This paper analyzes the concept connotation of system adaptability, system integration degree and system contribution rate, defines the construction principles and ideas of equipment system adaptability evaluation index system, and establishes an index system reflecting the adaptability of military communication equipment system from two aspects of system integration degree and system contribution rate, so as to provide theoretical reference and technical support for military communication equipment system adaptability evaluation.","PeriodicalId":354966,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Application Engineering","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125584458","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
Design of Data Acquisition Scheme of MES System for Frame Production Line 车架生产线MES系统数据采集方案设计
Proceedings of the 5th International Conference on Computer Science and Application Engineering Pub Date : 2021-10-19 DOI: 10.1145/3487075.3487144
Kaiwei Yang, T. Jin, Yi Tong
{"title":"Design of Data Acquisition Scheme of MES System for Frame Production Line","authors":"Kaiwei Yang, T. Jin, Yi Tong","doi":"10.1145/3487075.3487144","DOIUrl":"https://doi.org/10.1145/3487075.3487144","url":null,"abstract":"For manufacturing companies, the ability to collect accurate, comprehensive, and real-time production process data is very beneficial to the refined management of the company. Based on technologies such as PLC and Code39 barcodes, this paper designs a data acquisition scheme for the data acquisition module of the MES system of a frame production line in an enterprise. First of all, it analyzes and summarizes the problems existing in the data collection link of the production line. Then, according to the data objects, the corresponding data collection schemes are designed. Practice has proved that the data collection program designed in this paper has brought certain reference value to the enterprise.","PeriodicalId":354966,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Application Engineering","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132523746","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
Smoky Vehicle Detection Based on Improved Vision Transformer 基于改进视觉变压器的车辆烟雾检测
Proceedings of the 5th International Conference on Computer Science and Application Engineering Pub Date : 2021-10-19 DOI: 10.1145/3487075.3487172
Li Yuan, Shuzhen Tong, Xiaobo Lu
{"title":"Smoky Vehicle Detection Based on Improved Vision Transformer","authors":"Li Yuan, Shuzhen Tong, Xiaobo Lu","doi":"10.1145/3487075.3487172","DOIUrl":"https://doi.org/10.1145/3487075.3487172","url":null,"abstract":"The harmful exhaust emissions of fuel vehicles in the world are damaging to human health and the environment, thus detecting smoky vehicles from real road environment is significant. At present, methods of smoky vehicle detection based on deep learning have the problem of high false-positive rate. To improve the performance, a two-stage video smoky vehicle detection algorithm based on the smoke classification in the core region from detected vehicle object boxes is proposed in this paper. Specifically, the vehicle object detection is realized by the algorithm based on YOLOv3. The smoke classification is realized by combining Vision Transformer and distillation, and the loss function is optimized in the training process. Experimental results on our smoky vehicle dataset have shown that the improved model achieves an F1 score over 0.4, precision over 0.4, recall nearly 0.1 improvement compared with the basic model, which can effectively reduce the false-positive rate during detection.","PeriodicalId":354966,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Application Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130000562","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
下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信