Pub Date : 2021-01-05DOI: 10.1109/ICCRD51685.2021.9386557
He Zhanquan, L. Xiaoqing, W. Shusheng, Qian YueZhen
Aiming at the characteristics of Polar codes, this paper proposes a noise-assisted Polar code attempt decoding algorithm based on the analysis of frame error rate and bit error rate to improve Polar code decoding performance. The basic principle of the algorithm is that when the encoded data frame is transmitted through the channel, the signal-to-noise ratio is decreased. When the received signal exceeds the decoding capability and cannot be decoded normally, the auxiliary man-made noise is added to make the received signal to have a lower decision probability. The addition of low-power man-made noise will result in further randomization of the region with poor reliability of the original sampled data signal (close to zeros for BPSK modulation), and the bit rollover probability of the higher reliability of the sampled data is smaller. Under this condition, attempt to decode, if check data correct, decode finished, otherwise regenerate man-made noise for the next attempt until the decoding passes or reaches the maximum. This algorithm is a post-compensation processing method for existing algorithms, which play an incremental role.
{"title":"A Noise-Assisted Polar Code Attempt Decoding Algorithm","authors":"He Zhanquan, L. Xiaoqing, W. Shusheng, Qian YueZhen","doi":"10.1109/ICCRD51685.2021.9386557","DOIUrl":"https://doi.org/10.1109/ICCRD51685.2021.9386557","url":null,"abstract":"Aiming at the characteristics of Polar codes, this paper proposes a noise-assisted Polar code attempt decoding algorithm based on the analysis of frame error rate and bit error rate to improve Polar code decoding performance. The basic principle of the algorithm is that when the encoded data frame is transmitted through the channel, the signal-to-noise ratio is decreased. When the received signal exceeds the decoding capability and cannot be decoded normally, the auxiliary man-made noise is added to make the received signal to have a lower decision probability. The addition of low-power man-made noise will result in further randomization of the region with poor reliability of the original sampled data signal (close to zeros for BPSK modulation), and the bit rollover probability of the higher reliability of the sampled data is smaller. Under this condition, attempt to decode, if check data correct, decode finished, otherwise regenerate man-made noise for the next attempt until the decoding passes or reaches the maximum. This algorithm is a post-compensation processing method for existing algorithms, which play an incremental role.","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"45 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120922551","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 : 2021-01-05DOI: 10.1109/ICCRD51685.2021.9386349
Wenting Xu, Ruiguo Liu, Weifeng Zhang, Z. Chao, F. Jia
The detection of surgical actions and instruments plays a very important role in computer-assisted endoscopic surgery. However, organ deformation and narrow surgical field increase the task difficulty. Accordingly, the problems of the detection of surgical actions and instruments have not been solved yet. In this paper, we proposed a multiscale fusion feature pyramid network (MSF-FPN) to merge low-level semantic information and high-level semantic information. Firstly, the feature map effectively aggregates the information by the initial layer of the pyramid network, and then diverges after the cross-transmission of the feature information in the middle layer. Finally, a strong semantic feature map was obtained in the output layer. Experiments verified that the average precision of the proposed MSF-FPN on the public endoscopic surgeon action detection (ESAD) dataset is increased by 2.9% and 1.5% compared with the general FPN and path aggregation network (PANet), and the average precision on the proposed cataract-based object detection (COD) dataset is increased by 4.3% and 2.6%, respectively.
{"title":"Surgical Action and Instrument Detection Based on Multiscale Information Fusion","authors":"Wenting Xu, Ruiguo Liu, Weifeng Zhang, Z. Chao, F. Jia","doi":"10.1109/ICCRD51685.2021.9386349","DOIUrl":"https://doi.org/10.1109/ICCRD51685.2021.9386349","url":null,"abstract":"The detection of surgical actions and instruments plays a very important role in computer-assisted endoscopic surgery. However, organ deformation and narrow surgical field increase the task difficulty. Accordingly, the problems of the detection of surgical actions and instruments have not been solved yet. In this paper, we proposed a multiscale fusion feature pyramid network (MSF-FPN) to merge low-level semantic information and high-level semantic information. Firstly, the feature map effectively aggregates the information by the initial layer of the pyramid network, and then diverges after the cross-transmission of the feature information in the middle layer. Finally, a strong semantic feature map was obtained in the output layer. Experiments verified that the average precision of the proposed MSF-FPN on the public endoscopic surgeon action detection (ESAD) dataset is increased by 2.9% and 1.5% compared with the general FPN and path aggregation network (PANet), and the average precision on the proposed cataract-based object detection (COD) dataset is increased by 4.3% and 2.6%, respectively.","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132215043","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 : 2021-01-05DOI: 10.1109/ICCRD51685.2021.9386703
Boxuan Shan
In recent years, the application range of blockchain has become more and more extensive. This paper proposed a volunteer computing system design based on the blockchain. This system takes advantage of the decentralized, persistent and auditable characteristics of the blockchain to solve the scalability and single point of failure problem under the traditional centralized C/S framework and provides a certain traceability for volunteer calculations. Increased scalability implies that the system can accommodate more computing jobs and participants. Solving the single-point failure problem implies that the volunteer computing system can provide researchers with longer-term and more stable computing resources. The traceability implies that anyone can view the blockchain to understand which volunteers have participated in every computing work in history and the adoption of the results provided by each volunteer. At the same time, with the help of the persistence and auditability of the blockchain, the authenticity of history can be ensured. This paper studies the C/S framework volunteer computing as well as blockchain, and proposes a framework for volunteer computing based on the blockchain. Then discussed its pros and cons in terms of feasibility, scalability, security, authenticity, traceability etc.
{"title":"A Design of Volunteer Computing System Based on Blockchain","authors":"Boxuan Shan","doi":"10.1109/ICCRD51685.2021.9386703","DOIUrl":"https://doi.org/10.1109/ICCRD51685.2021.9386703","url":null,"abstract":"In recent years, the application range of blockchain has become more and more extensive. This paper proposed a volunteer computing system design based on the blockchain. This system takes advantage of the decentralized, persistent and auditable characteristics of the blockchain to solve the scalability and single point of failure problem under the traditional centralized C/S framework and provides a certain traceability for volunteer calculations. Increased scalability implies that the system can accommodate more computing jobs and participants. Solving the single-point failure problem implies that the volunteer computing system can provide researchers with longer-term and more stable computing resources. The traceability implies that anyone can view the blockchain to understand which volunteers have participated in every computing work in history and the adoption of the results provided by each volunteer. At the same time, with the help of the persistence and auditability of the blockchain, the authenticity of history can be ensured. This paper studies the C/S framework volunteer computing as well as blockchain, and proposes a framework for volunteer computing based on the blockchain. Then discussed its pros and cons in terms of feasibility, scalability, security, authenticity, traceability etc.","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131199398","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 : 2021-01-05DOI: 10.1109/ICCRD51685.2021.9386518
Jun Shao, Liang Chen, Yi Wu
The study of generative adversarial networks (GAN) has enormously promoted the research work on single image super-resolution (SISR) problem. SRGAN firstly apply GAN to SISR reconstruction, which has achieved good results. However, SRGAN sacrifices the fidelity. At the same time, it is well known that the GANs are difficult to train and the improper training fails the SISR results easily. Recently, Wasserstein Generative Adversarial Network with gradient penalty (WGAN-GP) has been proposed to alleviate these issues at the expense of performance of the model with a relatively simple training process. However, we find that applying WGAN-GP to SISR still suffers from training instability, leading to failure to obtain a good SR result. To address this problem, we present an image super resolution framework base on enhanced WGAN (SRWGAN-TV). We introduce the total variational (TV) regularization term into the loss function of WGAN. The total variational (TV) regularization term can stabilize the network training and improve the quality of generated images. Experimental results on public datasets show that the proposed method achieves superior performance in both quantitative and qualitative measurements.
{"title":"SRWGANTV: Image Super-Resolution Through Wasserstein Generative Adversarial Networks with Total Variational Regularization","authors":"Jun Shao, Liang Chen, Yi Wu","doi":"10.1109/ICCRD51685.2021.9386518","DOIUrl":"https://doi.org/10.1109/ICCRD51685.2021.9386518","url":null,"abstract":"The study of generative adversarial networks (GAN) has enormously promoted the research work on single image super-resolution (SISR) problem. SRGAN firstly apply GAN to SISR reconstruction, which has achieved good results. However, SRGAN sacrifices the fidelity. At the same time, it is well known that the GANs are difficult to train and the improper training fails the SISR results easily. Recently, Wasserstein Generative Adversarial Network with gradient penalty (WGAN-GP) has been proposed to alleviate these issues at the expense of performance of the model with a relatively simple training process. However, we find that applying WGAN-GP to SISR still suffers from training instability, leading to failure to obtain a good SR result. To address this problem, we present an image super resolution framework base on enhanced WGAN (SRWGAN-TV). We introduce the total variational (TV) regularization term into the loss function of WGAN. The total variational (TV) regularization term can stabilize the network training and improve the quality of generated images. Experimental results on public datasets show that the proposed method achieves superior performance in both quantitative and qualitative measurements.","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133493683","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 : 2021-01-05DOI: 10.1109/ICCRD51685.2021.9386369
Xinfeng Zhang, Lisha Zuo, Baoqing Yang, Shuhan Chen, Bin Li
The crowd counting in public places is a wildly concerned issue in the fields of public safety, activity planning, and space design. The current crowd counting methods are mainly aimed at the situation that the crowd is full of the whole scene, which cannot be applied to practical applications due to the actual crowd is non-uniform distributed in the scene. The complex background caused by non-uniform population distribution affects the accuracy of crowd counting. Therefore, we propose a convolutional neural network with background exclusion for crowd counting. Firstly, we divide the image into blocks and then use the residual network to determine whether each block contains crowd, to eliminate the clutter background area and avoid the background interference to crowd counting. Secondly, we use the dilated convolution and asymmetric convolution to estimate the crowd density map of image blocks containing crowd. Finally, the crowd density map of all crowd areas is integrated to obtain the crowd counting results of the whole scene. We collect some images of more general scenes, such as the crowd is only a part of the whole image, and construct Non-uniformly Distributed Crowd (NDC 2020) dataset. We conduct experiments on ShanghaiTech datasets and NDC 2020 dataset. Experiment results show that our method is superior to the existing crowd counting methods in the scene of non-uniform population distribution.
{"title":"A Convolutional Neural Network with Background Exclusion for Crowd Counting in Non-uniform Population Distribution Scenes","authors":"Xinfeng Zhang, Lisha Zuo, Baoqing Yang, Shuhan Chen, Bin Li","doi":"10.1109/ICCRD51685.2021.9386369","DOIUrl":"https://doi.org/10.1109/ICCRD51685.2021.9386369","url":null,"abstract":"The crowd counting in public places is a wildly concerned issue in the fields of public safety, activity planning, and space design. The current crowd counting methods are mainly aimed at the situation that the crowd is full of the whole scene, which cannot be applied to practical applications due to the actual crowd is non-uniform distributed in the scene. The complex background caused by non-uniform population distribution affects the accuracy of crowd counting. Therefore, we propose a convolutional neural network with background exclusion for crowd counting. Firstly, we divide the image into blocks and then use the residual network to determine whether each block contains crowd, to eliminate the clutter background area and avoid the background interference to crowd counting. Secondly, we use the dilated convolution and asymmetric convolution to estimate the crowd density map of image blocks containing crowd. Finally, the crowd density map of all crowd areas is integrated to obtain the crowd counting results of the whole scene. We collect some images of more general scenes, such as the crowd is only a part of the whole image, and construct Non-uniformly Distributed Crowd (NDC 2020) dataset. We conduct experiments on ShanghaiTech datasets and NDC 2020 dataset. Experiment results show that our method is superior to the existing crowd counting methods in the scene of non-uniform population distribution.","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"9 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123782000","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 : 2021-01-05DOI: 10.1109/ICCRD51685.2021.9386366
Ren Liu, Ziang Ren
2020 has been a year marked by the COVID-19 pandemic. This event has caused disruptions to many aspects of normal life. An important aspect in reducing the impact of the pandemic is to control its spread. Studies have shown that one effective method in reducing the transmission of COVID-19 is to wear masks. Strict mask-wearing policies have been met with not only public sensation but also practical difficulty. We cannot hope to manually check if everyone on a street is wearing a mask properly. Existing technology to help automate mask checking uses deep learning models on real-time surveillance camera footages. The current dominant method to perform real-time mask detection uses Mask-R-CNN with ResNet as backbone. While giving good detection results, this method is computationally intensive and its efficiency in real-time face mask detection is not ideal. Our research proposes a new approach to the mask detection by replacing Mask-R-CNN with a more efficient model "YOLO" to increase the processing speed of real-time mask detection and not compromise on accuracy. Besides, given the small volume as well as extreme imbalance of the mask detection datasets, we adopt a latest progress made in few-shot visual classification, simple CNAPs, to improve the classification performance.
2020年是2019冠状病毒病大流行的一年。这一事件对正常生活的许多方面造成了干扰。减少这一流行病影响的一个重要方面是控制其传播。研究表明，戴口罩是减少新冠病毒传播的有效方法之一。严格的戴口罩政策不仅在公众中引起轰动，而且在实践中也遇到了困难。我们不能指望手动检查街上的每个人是否都戴了口罩。现有的帮助自动检查掩模的技术是在实时监控摄像头的画面上使用深度学习模型。目前主要的实时掩码检测方法是以ResNet为骨干的mask - r - cnn。该方法在获得较好的检测结果的同时，计算量较大，在实时检测中效率不理想。我们的研究提出了一种新的掩码检测方法，用更高效的“YOLO”模型代替mask - r - cnn，提高实时掩码检测的处理速度，同时不影响精度。此外，由于蒙版检测数据集体积小且极不平衡，我们采用了少镜头视觉分类的最新进展——简单的CNAPs来提高分类性能。
{"title":"Application of Yolo on Mask Detection Task","authors":"Ren Liu, Ziang Ren","doi":"10.1109/ICCRD51685.2021.9386366","DOIUrl":"https://doi.org/10.1109/ICCRD51685.2021.9386366","url":null,"abstract":"2020 has been a year marked by the COVID-19 pandemic. This event has caused disruptions to many aspects of normal life. An important aspect in reducing the impact of the pandemic is to control its spread. Studies have shown that one effective method in reducing the transmission of COVID-19 is to wear masks. Strict mask-wearing policies have been met with not only public sensation but also practical difficulty. We cannot hope to manually check if everyone on a street is wearing a mask properly. Existing technology to help automate mask checking uses deep learning models on real-time surveillance camera footages. The current dominant method to perform real-time mask detection uses Mask-R-CNN with ResNet as backbone. While giving good detection results, this method is computationally intensive and its efficiency in real-time face mask detection is not ideal. Our research proposes a new approach to the mask detection by replacing Mask-R-CNN with a more efficient model \"YOLO\" to increase the processing speed of real-time mask detection and not compromise on accuracy. Besides, given the small volume as well as extreme imbalance of the mask detection datasets, we adopt a latest progress made in few-shot visual classification, simple CNAPs, to improve the classification performance.","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133842497","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 : 2021-01-05DOI: 10.1109/ICCRD51685.2021.9386597
Zihui Zhang, Zongyao Hu
Finding that not all dictionary atoms are closely related to degradation in visual signal, we innovatively design a distortion sensitivity guided Dynamic Atom Classification (DAC) strategy to separate distorted signal. Then, we propose a novel DAC-based full-reference video quality assessment (VQA) method. The method includes two parts: spatial quality evaluation and temporal quality evaluation. Spatially, we train a distortion-aware dictionary, get sparse representation of video patches, and dynamically classify activated dictionary atoms. Every frame is separated into difference and basic components, and spatial similarity is aggregated by component similarities. Temporally, we calculate gradient similarity of frame difference to capture motion information. The experimental results indicate the effectiveness of the proposed algorithm compared with state-of-art VQA methods.
{"title":"Video Quality Assessment by Sparse Representation and Dynamic Atom Classification","authors":"Zihui Zhang, Zongyao Hu","doi":"10.1109/ICCRD51685.2021.9386597","DOIUrl":"https://doi.org/10.1109/ICCRD51685.2021.9386597","url":null,"abstract":"Finding that not all dictionary atoms are closely related to degradation in visual signal, we innovatively design a distortion sensitivity guided Dynamic Atom Classification (DAC) strategy to separate distorted signal. Then, we propose a novel DAC-based full-reference video quality assessment (VQA) method. The method includes two parts: spatial quality evaluation and temporal quality evaluation. Spatially, we train a distortion-aware dictionary, get sparse representation of video patches, and dynamically classify activated dictionary atoms. Every frame is separated into difference and basic components, and spatial similarity is aggregated by component similarities. Temporally, we calculate gradient similarity of frame difference to capture motion information. The experimental results indicate the effectiveness of the proposed algorithm compared with state-of-art VQA methods.","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"6 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126716878","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 : 2021-01-05DOI: 10.1109/ICCRD51685.2021.9386426
Tingliang Guan, Ding Wang, Yixin Su
Aiming at the problems of large positioning error and low positioning effect at the boundary of traditional RFID virtual tag positioning algorithm, this paper compares the influence of four different interpolation methods of virtual reference tag signal strength on positioning accuracy, and proposes a RFID virtual tag positioning algorithm based on Monte Carlo. The algorithm uses dynamic particles to replace the traditional static reference tag; introduces particle swarm optimization algorithm to update the Monte Carlo sample particle swarm, and gives different weights to the sampling particles based on the signal strength difference between the sampling particles and the undetermined tags, and finally completes the localization of the unknown tags through Monte Carlo resampling. The simulation results show that the algorithm can effectively improve the accuracy and stability of RFID positioning system compared with the traditional virtual tag positioning algorithm.
{"title":"Research on RFID Virtual Tag Location Algorithm Based on Monte Carlo","authors":"Tingliang Guan, Ding Wang, Yixin Su","doi":"10.1109/ICCRD51685.2021.9386426","DOIUrl":"https://doi.org/10.1109/ICCRD51685.2021.9386426","url":null,"abstract":"Aiming at the problems of large positioning error and low positioning effect at the boundary of traditional RFID virtual tag positioning algorithm, this paper compares the influence of four different interpolation methods of virtual reference tag signal strength on positioning accuracy, and proposes a RFID virtual tag positioning algorithm based on Monte Carlo. The algorithm uses dynamic particles to replace the traditional static reference tag; introduces particle swarm optimization algorithm to update the Monte Carlo sample particle swarm, and gives different weights to the sampling particles based on the signal strength difference between the sampling particles and the undetermined tags, and finally completes the localization of the unknown tags through Monte Carlo resampling. The simulation results show that the algorithm can effectively improve the accuracy and stability of RFID positioning system compared with the traditional virtual tag positioning algorithm.","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121513650","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 : 2021-01-05DOI: 10.1109/ICCRD51685.2021.9386475
Zhaochu Deng, Jianjiang Li, Jie Lin
In recent years, even though the chip density can still increase, it is difficult to increase the main frequency. Performance improvements for single processors may be close to their limits. So multi-core processors are coming on the scene. In order to make full use of multi-core platforms, we must find the inherent parallelism of programs and write programs that can execute in parallel. OpenMP standard is widely used in parallel programming because of its good portability and ease of use. For OpenMP programs generated by parallel compilers and OpenMP programs which only have simple parallelism, they belong to programs with insufficient optimization. In OpenMP parallel execution, synchronization control is one of the main overheads. Its unnecessary barrier synchronization reduces the performance of parallel program. This paper discusses an optimization technology of OpenMP program. Firstly, the parallel area of OpenMP program is merged and expanded to reduce the overhead of parallel and serial switching in execution, and at the same time, it is convenient for next steps to optimize the program. Then explicit the implicit synchronization in OpenMP program. Finally, data dependency analysis is carried out for the context of each synchronization, and unnecessary synchronizations are deleted. The program is tested with the program running time as an index to evaluate the performance of the test program. The experimental results show that the optimization strategy proposed in this paper correctly reconstructs the parallel regions and reduces its execution overhead; it reduces the number of redundant synchronizations and effectively improve the performance of OpenMP program.
{"title":"A Synchronization Optimization Technique for OpenMP","authors":"Zhaochu Deng, Jianjiang Li, Jie Lin","doi":"10.1109/ICCRD51685.2021.9386475","DOIUrl":"https://doi.org/10.1109/ICCRD51685.2021.9386475","url":null,"abstract":"In recent years, even though the chip density can still increase, it is difficult to increase the main frequency. Performance improvements for single processors may be close to their limits. So multi-core processors are coming on the scene. In order to make full use of multi-core platforms, we must find the inherent parallelism of programs and write programs that can execute in parallel. OpenMP standard is widely used in parallel programming because of its good portability and ease of use. For OpenMP programs generated by parallel compilers and OpenMP programs which only have simple parallelism, they belong to programs with insufficient optimization. In OpenMP parallel execution, synchronization control is one of the main overheads. Its unnecessary barrier synchronization reduces the performance of parallel program. This paper discusses an optimization technology of OpenMP program. Firstly, the parallel area of OpenMP program is merged and expanded to reduce the overhead of parallel and serial switching in execution, and at the same time, it is convenient for next steps to optimize the program. Then explicit the implicit synchronization in OpenMP program. Finally, data dependency analysis is carried out for the context of each synchronization, and unnecessary synchronizations are deleted. The program is tested with the program running time as an index to evaluate the performance of the test program. The experimental results show that the optimization strategy proposed in this paper correctly reconstructs the parallel regions and reduces its execution overhead; it reduces the number of redundant synchronizations and effectively improve the performance of OpenMP program.","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128248366","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 : 2021-01-05DOI: 10.1109/ICCRD51685.2021.9386491
Xueshun Ye, Kaiyuan He, Tianyuan Kang, Muke Bai
In order to solve the problem of optimal dispatching between source, network and flexible loads, and improve the safety and stability operation level of distribution network, this paper proposes a two stage multi-objective control method for distribution network. The first stage optimization control is the day ahead scheduling, the control objectives is source and load balance, and minimum of the longest path of feeder in distribution network. The second stage is hourly control, the control objectives of static voltage stability margin and the active power loss are used to effectively improve the coordination, safety, and economy of distribution network. An improved multi-objective harmony search algorithm is proposed to solve this two stage multi-objective optimization model. Finally, the effectiveness of the proposed two stage multi-objective control method is verified by IEEE 33 bus system with distributed generations.
{"title":"Two Stage Operation Optimization of Active Distribution Network Based on IMOHS Algorithm","authors":"Xueshun Ye, Kaiyuan He, Tianyuan Kang, Muke Bai","doi":"10.1109/ICCRD51685.2021.9386491","DOIUrl":"https://doi.org/10.1109/ICCRD51685.2021.9386491","url":null,"abstract":"In order to solve the problem of optimal dispatching between source, network and flexible loads, and improve the safety and stability operation level of distribution network, this paper proposes a two stage multi-objective control method for distribution network. The first stage optimization control is the day ahead scheduling, the control objectives is source and load balance, and minimum of the longest path of feeder in distribution network. The second stage is hourly control, the control objectives of static voltage stability margin and the active power loss are used to effectively improve the coordination, safety, and economy of distribution network. An improved multi-objective harmony search algorithm is proposed to solve this two stage multi-objective optimization model. Finally, the effectiveness of the proposed two stage multi-objective control method is verified by IEEE 33 bus system with distributed generations.","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130473207","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：