International Conference on Advanced Computational Intelligence最新文献

Fractional Complex-order Hopfield Neural Networks to Analyze the Effect of Drug-resistance in the HIV Infection 分数阶复阶Hopfield神经网络分析HIV感染耐药的影响

International Conference on Advanced Computational Intelligence Pub Date : 2020-08-01 DOI: 10.1109/ICACI49185.2020.9177513

C. Fernández

{"title":"Fractional Complex-order Hopfield Neural Networks to Analyze the Effect of Drug-resistance in the HIV Infection","authors":"C. Fernández","doi":"10.1109/ICACI49185.2020.9177513","DOIUrl":"https://doi.org/10.1109/ICACI49185.2020.9177513","url":null,"abstract":"The present paper uses a complex and fractional-order model for Hopfield neural networks to set a nonlinear model that represents the quantity of infected/uninfected CD4+T cells into the HIV dynamic when an antiviral therapy based on protease inhibitors is applied. By using a mathematical model of the environment associated with CD4+T cells that are progressively infected, it is proposed a closed-loop scheme associated with the HIV dynamic and its antiviral therapy, both acting in the same environment. To this end, the work reported here will use Caputo-type derivatives in order to represent such closed-loop dynamic by assuming that there is a nonlinear model based on Hopfield neural networks (HNN). In this way, the mutual interference between the additive activation dynamics of HNN and the complex-valued fractional-order analysis will be used to study the local and global asymptotic stability of HIV. The effect of drug-resistance will be the main starting point to understand how the resistant CD4+T cells can be reduced. The equilibrium point of HNN model will be studied by using quadratic-type Lyapunov functions and compared with a model based on Grunwald-Letnikov formulation in order to validate the approach proposed. The results show that HNN-based model converges toward a small neighborhood of the origin with better performance than Grunwald-Letnikov model.","PeriodicalId":346930,"journal":{"name":"International Conference on Advanced Computational Intelligence","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117248659","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

An Automatic Fracture Defect Detection Approach for Current-carrying Rings of Catenary Droppers Using A Multi-task Neural Network 基于多任务神经网络的悬链线载流环断裂缺陷自动检测方法

International Conference on Advanced Computational Intelligence Pub Date : 1900-01-01 DOI: 10.1109/ICACI49185.2020.9177502

Wenqiang Liu, Dan Wang, Yuyang Li, Cheng Yang, Hui Wang, Zhigang Liu

{"title":"An Automatic Fracture Defect Detection Approach for Current-carrying Rings of Catenary Droppers Using A Multi-task Neural Network","authors":"Wenqiang Liu, Dan Wang, Yuyang Li, Cheng Yang, Hui Wang, Zhigang Liu","doi":"10.1109/ICACI49185.2020.9177502","DOIUrl":"https://doi.org/10.1109/ICACI49185.2020.9177502","url":null,"abstract":"Catenary droppers play an essential role in the catenary system. They both connect messenger wires and contact wires to stabilize contact wires and transmit the working current and short-circuit current. And the current carrying rings of catenary droppers can avoid the direct connect of droppers and dropper clips and reduce electrical faults and arcs when the locomotive draws current through the pantograph. At present, researchers mainly focus on the loosen defect of droppers, but still do not pay attention to the fracture defect of the current-carrying ring of droppers. Therefore, this paper proposes an automatic fracture defect detection approach for the current-carrying ring of droppers using a multi-task neural network. Compared to traditional solutions based on the connected domains, the method based on neural networks is more automated and robust. First, this network consisted of three function head networks of a classification head network, a regression head network, and a mask head network is performed to get a classification score and a segmentation score, respectively. And then, by counting the scores of normal and faulty components, a fault criterion for evaluating the current-carrying ring is proposed. Experiment results show that the proposed method is highly accurate and automatic for the state detection of catenary droppers.","PeriodicalId":346930,"journal":{"name":"International Conference on Advanced Computational Intelligence","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125484345","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

Research on torque compensation control strategy for four-wheel drive hybrid system in rapid acceleration 四轮驱动混合动力系统快速加速转矩补偿控制策略研究

International Conference on Advanced Computational Intelligence Pub Date : 1900-01-01 DOI: 10.1109/ICACI.2018.8377584

Cui Liu, Wei Zhang, Jianhua Guo, Zuofei Liu

引用次数: 1

Multiple route planning algorithm based on improved K-means clustering and particle swarm optimization 基于改进k均值聚类和粒子群优化的多路径规划算法

International Conference on Advanced Computational Intelligence Pub Date : 1900-01-01 DOI: 10.1109/ICACI.2018.8377617

Hai-yan Yang, Shuai-wen Zhang, Cheng Han

引用次数: 1

Recognition of virtual maze scene under simulated prosthetic vision 模拟假体视觉下的虚拟迷宫场景识别

International Conference on Advanced Computational Intelligence Pub Date : 1900-01-01 DOI: 10.1109/ICACI.2018.8377543

Ying Zhao, Xiulin Geng, Qi Li, Guangqi Jiang

{"title":"Recognition of virtual maze scene under simulated prosthetic vision","authors":"Ying Zhao, Xiulin Geng, Qi Li, Guangqi Jiang","doi":"10.1109/ICACI.2018.8377543","DOIUrl":"https://doi.org/10.1109/ICACI.2018.8377543","url":null,"abstract":"To help blind people obtain the optimal vision in low resolution effectively, real-time maze pathfinding experiment under simulated prosthetic vision was carried out to find the optimal real-time scene processing strategy using the limited number of electrodes. Simple (5×5), medium (8×8) and complex (11×11) maze scenes were built by Unity. Then, binarization, color inversion and matching to 32×32 resolution phosphene template were performed as image processing strategy to get useful scene information from the camera and realize real-time pixelization. In the experiment, subjects were asked to complete 45 and 60 degrees viewpoint of the maze pathfinding task at 32×32 resolution. The time of finding entrance, maze pathfinding and the accuracy rate of completing maze from different view angles under the same resolution were recorded and analyzed to determine the optimal viewing angle. As the results, Subjects were able to accomplish the most complicated maze routing task at 32×32 resolution, the time of finding entrance under 45 degrees viewpoint and 60 degrees viewpoint were 14.38 seconds and 19.30 seconds, the time of 45 degrees viewpoint was significantly less than that of 60 degrees. The time of the maze pathfinding under two view angles were 125.39 seconds and 170.14 seconds, and the time of 45 degrees viewpoint was less than that of 60 degrees. Therefore, the 45 degrees viewpoint was significantly better than the 60 degrees visual angle and provided the best viewpoint for visual prosthesis to complete maze wayfinding tasks.","PeriodicalId":346930,"journal":{"name":"International Conference on Advanced Computational Intelligence","volume":"170 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124136946","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

Image Block Compression Based on Dual-Learning Dictionaries 基于双学习字典的图像块压缩

International Conference on Advanced Computational Intelligence Pub Date : 1900-01-01 DOI: 10.1109/ICACI49185.2020.9177627

Wen-ling Pan, Bo Li, Yanwen Chong

引用次数: 1

Max-margin generative adversarial networks 最大边际生成对抗网络

International Conference on Advanced Computational Intelligence Pub Date : 1900-01-01 DOI: 10.1109/ICACI.2018.8377529

Wanshun Gao, Zhonghao Wang

引用次数: 0

BOF Endpoint Carbon Content Prediction based on Association Rule Case Base Maintenance Strategy 基于关联规则案例维护策略的转炉终点含碳量预测

International Conference on Advanced Computational Intelligence Pub Date : 1900-01-01 DOI: 10.1109/ICACI49185.2020.9177854

Yuan Cheng, Z. Cheng, Xinzhe Wang

引用次数: 0

Visualization analysis of shipping recruitment information based on R 基于R的航运招聘信息可视化分析

International Conference on Advanced Computational Intelligence Pub Date : 1900-01-01 DOI: 10.1109/ICACI.2018.8377582

Yang Wang, Ye Tian, Tiefeng Li, Dongcheng Peng, Yihua Zhou

{"title":"Visualization analysis of shipping recruitment information based on R","authors":"Yang Wang, Ye Tian, Tiefeng Li, Dongcheng Peng, Yihua Zhou","doi":"10.1109/ICACI.2018.8377582","DOIUrl":"https://doi.org/10.1109/ICACI.2018.8377582","url":null,"abstract":"With the combination of big data and shipping industry, data visualization plays a more and more important role in the shipping industry, which makes the boring industry data vivid and intuitive and help users understand and grasp the data easily. However, the traditional data visualization has a series of deficiencies, for instance, the display structure is too single and too simple, the unit information is insufficient, the visualization function for the multi-factor data set is limited, which has become increasingly unable to meet people's requirements for visualization. In this paper, we apply Python web crawler for crawling the shipping recruitment information firstly. Then, do some necessary data preprocessing through the R language based on reshape software package, next we use one of the ggplot2 software package to do a variety of visualization of shipping recruitment information. Finally, some necessary analysis and assessment have been made according to the visualization results and some relevant professional knowledge. The experimental results show that the ggplot2 drawing system can deal with the multi-factor shipping recruitment information dataset and can design the graph with high recognition and large information. In addition, according to the visualization results, this paper can easily find out the significant level of each factor and the trend of each level, which to be expected to provide a reference and basis for the determination of the overall situation of China's seafarer market.","PeriodicalId":346930,"journal":{"name":"International Conference on Advanced Computational Intelligence","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114876787","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

Availability analysis of electronic flight instrument system based on dynamic fault tree 基于动态故障树的电子飞行仪表系统可用性分析

International Conference on Advanced Computational Intelligence Pub Date : 1900-01-01 DOI: 10.1109/ICACI.2018.8377503

Haiyong Dong, Guoqing Wang, Zhengjun Zhai, Yanhong Lu, Qingfan Gu

引用次数: 1