2021 6th International Conference on Computational Intelligence and Applications (ICCIA)最新文献

Improved Faster R-CNN for Automatic Video Annotations 改进更快的R-CNN自动视频注释

2021 6th International Conference on Computational Intelligence and Applications (ICCIA) Pub Date : 2021-06-01 DOI: 10.1109/ICCIA52886.2021.00048

Qing Liu, Ziyu Xue, Lei Wang, Peiyu Guo

{"title":"Improved Faster R-CNN for Automatic Video Annotations","authors":"Qing Liu, Ziyu Xue, Lei Wang, Peiyu Guo","doi":"10.1109/ICCIA52886.2021.00048","DOIUrl":"https://doi.org/10.1109/ICCIA52886.2021.00048","url":null,"abstract":"With the development of digital multimedia, how to manage a large amount of existing and incremental media assets has become an urgent problem. With the development of machine learning, the use of object detection framework to achieve intelligent cataloging and intelligent management of media assets will greatly improve work efficiency. Currently, Faster R-CNN is used quite often in intelligent cataloging, but the framework has the problem of low accuracy using feature extraction networks. In view of this, based on the Faster R-CNN object detection framework with VGG-16 as the feature extraction network, a novel object detection framework (DF-Faster R-CNN) was designed with ResNet-101 as the feature extraction network in this paper, which improved the recognition precision of the object detection framework. Compared with the current mainstream methods, the improved model proposed in this paper can effectively identify objects with overlap, occlusion and blur objects in the video, and is more suitable for image recognition in film and television works. The test results of this method on the MSCOCO data set show that compared with mainstream framework such as Fast R-CNN, Faster R-CNN, Pelee, and SIN, the method is significantly improved on mAP, and also has a higher precision in the ten types of object recognition experiments in PASCAL VOC dataset.","PeriodicalId":269269,"journal":{"name":"2021 6th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129877090","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 Knowledge Graph Based on Artistes’ Works 基于艺术家作品的知识图谱研究

2021 6th International Conference on Computational Intelligence and Applications (ICCIA) Pub Date : 2021-06-01 DOI: 10.1109/ICCIA52886.2021.00050

Fangyuan Ju, Xinyi Zhou, Ying Zhou, Xinyi Jiang, Sitong Li

引用次数: 0

Research on Optimization of Integrated Probabilistic Design Framework for Missile IGC under Massive Operating Conditions 大规模工况下导弹IGC综合概率设计框架优化研究

2021 6th International Conference on Computational Intelligence and Applications (ICCIA) Pub Date : 2021-06-01 DOI: 10.1109/ICCIA52886.2021.00051

Changmao Qin, Zhang Xin, Liu Wenxuan, Tian Dong

{"title":"Research on Optimization of Integrated Probabilistic Design Framework for Missile IGC under Massive Operating Conditions","authors":"Changmao Qin, Zhang Xin, Liu Wenxuan, Tian Dong","doi":"10.1109/ICCIA52886.2021.00051","DOIUrl":"https://doi.org/10.1109/ICCIA52886.2021.00051","url":null,"abstract":"In order to adapt to the development trend of low-cost, digital missiles, to meet the needs of refined design, rapid equipment formation, and enhancement of combat capabilities, missile guidance and control integrated probabilistic design simulation has been widely used. With the diversified development of research tasks and status, calculation conditions and data processing capacity have increased several times or even dozens of times, which puts forward higher requirements for design efficiency and rapid analysis capabilities. This paper conducts an in-depth investigation and study of the probabilistic design operation process and method, cycle and cost, and determines the main influencing factors by extracting the internal commonality and reason analysis. It proposes a targeted improvement method for the simulation platform architecture optimization. The application effect shows that this method can effectively improve the efficiency of probabilistic design simulation, and can effectively reduce the design cycle and cost under the simulation of massive working conditions. It has engineering practical value.","PeriodicalId":269269,"journal":{"name":"2021 6th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"370 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121741404","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 Constrained Multiobjective Evolutionary Algorithm based on State Transition Strategy 基于状态转移策略的约束多目标进化算法

2021 6th International Conference on Computational Intelligence and Applications (ICCIA) Pub Date : 2021-06-01 DOI: 10.1109/ICCIA52886.2021.00016

Jinhua Zheng, Jing Li, Tian Chen, Shengxiang Yang

{"title":"A Constrained Multiobjective Evolutionary Algorithm based on State Transition Strategy","authors":"Jinhua Zheng, Jing Li, Tian Chen, Shengxiang Yang","doi":"10.1109/ICCIA52886.2021.00016","DOIUrl":"https://doi.org/10.1109/ICCIA52886.2021.00016","url":null,"abstract":"Constrained multiobjective problems (CMOPs) are often encountered in many real-world applications which is difficult to solve because the relationship between constraints and objectives is not well balanced. To more specific, complex constraints may cause algorithms trapped in local optimum or even cannot find the feasible region. Thus, the importance of constraint multiobjective evolutionary algorithms (CMOEAs) is how to deal with constraints. In order to handling CMOPs, this paper proposed a strategy to solve the CMOPs which is named state transition based on constraint (STC). By judging whether the search gets trapped in the local optimum or reaches the unconstrained pareto front in the process of optimization, STC can adjust the value to controlling constraint handling technique (CHT) that help evolution of the population. This STC strategy is embedded in decomposition evolutionary algorithm (MOEA/D). The algorithm is compared with three state-of-the-art constrained multiobjective evolutionary algorithms (CMOEAs) on 16 typical constrained benchmark problems. The experimental results show that the proposed algorithm can effectively tackle with CMOPs.","PeriodicalId":269269,"journal":{"name":"2021 6th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"167 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134189291","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 Mechanism of Motion Direction Detection Based on Hassenstein-Reichardt Model 基于Hassenstein-Reichardt模型的运动方向检测机制

2021 6th International Conference on Computational Intelligence and Applications (ICCIA) Pub Date : 2021-06-01 DOI: 10.1109/ICCIA52886.2021.00042

Chenyang Yan, Yuki Todo, Zheng Tang

{"title":"The Mechanism of Motion Direction Detection Based on Hassenstein-Reichardt Model","authors":"Chenyang Yan, Yuki Todo, Zheng Tang","doi":"10.1109/ICCIA52886.2021.00042","DOIUrl":"https://doi.org/10.1109/ICCIA52886.2021.00042","url":null,"abstract":"Motion direction detection is an important part of the visual system. In the past few decades, research on the directional selectivity of motion detection is of great progress. However, they are all concentrated on the cellular level and lack a full understanding in systemic level. To understand motion direction detection, we present a novel motion detection mechanism using the Hassenstein-Reichardt (HR) model. We mimic a subunit of the HR model, propose a local motion direction detective neuron which can detect a specific direction of motion by performing a multiplication operation on one photoreceptor input with a fixed temporal delay and its adjacent photoreceptor input without delay. The proposed neuron can be extended to a two-dimensional vision, for ease of understanding, 8 neurons are implemented in detecting 8 directions of motion. Furthermore, we assume that each photoreceptor in the receptive field has its own local motion direction detective neurons and therefore we can obtain the global motion direction by accumulating the number of activations of all local motion direction detective neurons. The computer simulations have validated that the mechanism we proposed is reliable. We believe it may provide a strong support in understanding motion direction detection and other more complex processing in the visual system.","PeriodicalId":269269,"journal":{"name":"2021 6th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131263568","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

FPGA-based UAV Heterogeneous Computing Platform Architecture 基于fpga的无人机异构计算平台架构

2021 6th International Conference on Computational Intelligence and Applications (ICCIA) Pub Date : 2021-06-01 DOI: 10.1109/ICCIA52886.2021.00056

Junpeng Guo, Bo Jiang, Hong-xun Xu

引用次数: 0

A Real-time Image Processing Hardware Acceleration Method based on FPGA 基于FPGA的实时图像处理硬件加速方法

2021 6th International Conference on Computational Intelligence and Applications (ICCIA) Pub Date : 2021-06-01 DOI: 10.1109/ICCIA52886.2021.00046

Haiying Yuan, Dong Ding, Zhongwei Fan, Zengyang Sun

{"title":"A Real-time Image Processing Hardware Acceleration Method based on FPGA","authors":"Haiying Yuan, Dong Ding, Zhongwei Fan, Zengyang Sun","doi":"10.1109/ICCIA52886.2021.00046","DOIUrl":"https://doi.org/10.1109/ICCIA52886.2021.00046","url":null,"abstract":"Real-time image sensed by the visual sensor usually contains a lot of noise information. Model reasoning, and pattern recognition-oriented CNNs face such thorny issues as excessive computation, poor accuracy and high resource occupancy. Hence, CNN architecture was heterogeneously deployed on the Zynq platform to realize hardware acceleration for the image processing algorithm. MNIST dataset was adopted to train CNN for extracting network parameters on PC terminal under the Caffe framework; the convolutional layer responsible for heavy computational load was deployed onto FPGA for parallel computing to increase system speed; input layer and output layer responsible for a small amount computation were placed on ARM terminal to reduce resource consumption; real-time image acquired by the camera was binarized to highlight image features and improve the recognition accuracy; the hardware acceleration performance of the heterogeneously deployed CNN was verified with numerous experiments on image recognition of handwritten numerals. Experimental results indicated that: CNN hardware accelerator kept an image recognition accuracy up to 99.02% which is largely equivalent to that of client PC; When recognizing a single piece of handwritten numerical sample, under the use of optimized instructions and 100MHz clock frequency, the recognition time of a single image is 0.53s, which is 16 times faster than pure ARM operation; the maximum power consumption of the system is 2.606W, which is far Lower than general-purpose processors.","PeriodicalId":269269,"journal":{"name":"2021 6th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127738843","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 Preliminary Study of Evolutionary Multitasking for Multiobjective Vehicle Routing Problem With Time Windows 带时间窗的多目标车辆路径问题的进化多任务初探

2021 6th International Conference on Computational Intelligence and Applications (ICCIA) Pub Date : 2021-06-01 DOI: 10.1109/ICCIA52886.2021.00058

M. Cheng, Yiqiao Cai, Shunkai Fu

{"title":"A Preliminary Study of Evolutionary Multitasking for Multiobjective Vehicle Routing Problem With Time Windows","authors":"M. Cheng, Yiqiao Cai, Shunkai Fu","doi":"10.1109/ICCIA52886.2021.00058","DOIUrl":"https://doi.org/10.1109/ICCIA52886.2021.00058","url":null,"abstract":"Currently, most researches on multiobjective optimization (MOO) focus on solving only a single problem from the scratch during the search process, without the effective use of valuable knowledge from other related problems. It may lead to inefficient and repeated searches on similar problems. In recent years, with the rapid development of the cloud computing industry, evolutionary multitasking optimization (EMO) has attracted lots of attention and has shown its superior performance in solving multiple related problems simultaneously. Based on these considerations, we propose a novel EMO algorithm to solve multiple multiobjective vehicle routing problems with time windows (MOVRPTW) concurrently by combining the EMO framework with an off-the-shelf multiobjective optimization algorithm. The proposed algorithm is termed MMOVRPTW. In the proposed algorithm, a cooperation mechanism is designed to adaptively switch the search between the knowledge transfer process and the local search process. To evaluate the efficacy of the proposed algorithm, the preliminary study on the multitasking MOVRPTW benchmark problems by pairing the 45 real-world instances is carried out to compare MMOVRPTW with its single-task counterpart. The experimental results have demonstrated the advantages of the proposed algorithm for solving multiple MOVRPTW simultaneously.","PeriodicalId":269269,"journal":{"name":"2021 6th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134344975","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

Fine-grained Classification of Malicious Code Based on CNN and Multi-resolution Feature Fusion 基于CNN和多分辨率特征融合的恶意代码细粒度分类

2021 6th International Conference on Computational Intelligence and Applications (ICCIA) Pub Date : 2021-06-01 DOI: 10.1109/ICCIA52886.2021.00031

Junmiao Liang, Zhenhu Ning, Yihua Zhou, Dongzhi Cao

{"title":"Fine-grained Classification of Malicious Code Based on CNN and Multi-resolution Feature Fusion","authors":"Junmiao Liang, Zhenhu Ning, Yihua Zhou, Dongzhi Cao","doi":"10.1109/ICCIA52886.2021.00031","DOIUrl":"https://doi.org/10.1109/ICCIA52886.2021.00031","url":null,"abstract":"With the development of the Internet, security issues in the network have attracted more and more attention. Variants of malicious code are constantly increasing, and their attacks will have a serious impact on the network environment, so effective detection of malicious code has important research significance. However, the current malicious code detection methods still have some problems, such as code detection, cumbersome feature extraction, and misclassification between similar families. To this end, the paper proposes a fine-grained detection method for malicious code. First visualized the binary files of malicious code and converted them into grayscale images. Then, use the improved convolutional neural network to extract the multi-resolution features of grayscale images, and use the interactive fusion method to fuse these features. Finally, input the fused features into the fully connected layer to complete the fine-grained classification of malicious code. Experiments prove that our method is indeed effective for fine-grained classification of malicious code.","PeriodicalId":269269,"journal":{"name":"2021 6th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122877898","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 Distributed Learning Algorithm for RBF Neural Networks RBF神经网络的分布式学习算法

2021 6th International Conference on Computational Intelligence and Applications (ICCIA) Pub Date : 2021-06-01 DOI: 10.1109/ICCIA52886.2021.00059

Jing Dong, Liu Yang, Xiao-qing Luo

引用次数: 0