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

Research on Intelligent Diagnosis Model of Electronic Medical Record Based on Graph Transformer 基于图转换器的电子病历智能诊断模型研究

2021 6th International Conference on Computational Intelligence and Applications (ICCIA) Pub Date : 2021-06-01 DOI: 10.1109/ICCIA52886.2021.00022

Xiaocong Liu, Huazhen Wang, T. He, Xionghui Gong

{"title":"Research on Intelligent Diagnosis Model of Electronic Medical Record Based on Graph Transformer","authors":"Xiaocong Liu, Huazhen Wang, T. He, Xionghui Gong","doi":"10.1109/ICCIA52886.2021.00022","DOIUrl":"https://doi.org/10.1109/ICCIA52886.2021.00022","url":null,"abstract":"Intelligent diagnosis based on the Electronic Medical Record (EMR) is an important research content of biomedical informatics. Recent studies have showed that graph representation learning methods can improve the performance of diagnosis prediction tasks by utilizing the graph structural information of EMR. However, the original EMR data often do not contain such complete and explicit structural information. It is challenging to learn EMR structural information from EMR data. In this paper, we propose a Statistics and Knowledge based Graph Transformer (S_K_GT) model to jointly learn EMR graph and perform diagnosis prediction tasks. Specifically, we firstly use conditional probability to initially construct the adjacency matrix of EMR graph and send it to Transformer encoder to further learn the connection relationship between EMR nodes. Then, we construct a knowledge attention network based on medical knowledge graph as expert knowledge to optimize the EMR graph deep learning process. Finally, we learn precise EMR graph representation for intelligent diagnosis. Experiments on EMR data in both Chinese and English show that the proposed model outperforms the state-of-the-art methods in all diagnosis prediction tasks.","PeriodicalId":269269,"journal":{"name":"2021 6th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"36 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":"127464204","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

Air Pollution Forecast Model Based on LSTM 基于LSTM的大气污染预测模型

2021 6th International Conference on Computational Intelligence and Applications (ICCIA) Pub Date : 2021-06-01 DOI: 10.1109/ICCIA52886.2021.00025

Ziyu Wei, Lirong Yan, Xiaodong Zhu, Jiayi Chen, Yuanyuan Chen

引用次数: 0

The Mechanism of Orientation Detection Based on Local Orientation-Selective Neuron 基于局部定向选择神经元的定向检测机制

2021 6th International Conference on Computational Intelligence and Applications (ICCIA) Pub Date : 2021-06-01 DOI: 10.1109/ICCIA52886.2021.00045

Bin Li, Yuki Todo, Zheng Tang

{"title":"The Mechanism of Orientation Detection Based on Local Orientation-Selective Neuron","authors":"Bin Li, Yuki Todo, Zheng Tang","doi":"10.1109/ICCIA52886.2021.00045","DOIUrl":"https://doi.org/10.1109/ICCIA52886.2021.00045","url":null,"abstract":"Orientation detection is an essential function of the visual system. It is a basic behavior among creatures in nature and can directly affect animals’ behavioral decisions. Previously, Hubel and Wiesel studied cats’ and monkeys’ striate cortex and observed that some cells showed orientation selectivity in their response to one object. However, the mechanism of orientation selectivity, especially the global orientation detection of an object, is still an open problem. To Figure out this issue, we propose a new orientation detection mechanism based on local orientation-selective neurons to solve two-dimensional detection tasks. We assume that there are neurons only responsible for orientation detection in the brain, and each neuron is responsible only for detecting a local specific orientation. We use the McCulloch-Pitts neuron model to realize such neurons. The global orientation is obtained according to the number of orientation-selective neurons be activated. We performed computer simulations based on this mechanism, and the result shows that this mechanism works well for global orientation detection. This novel mechanism may lead to a brand-new pattern recognition method and promote the visual nervous system’s development.","PeriodicalId":269269,"journal":{"name":"2021 6th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"22 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":"115005148","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: 4

Teaching Path generation model based on machine learning 基于机器学习的教学路径生成模型

2021 6th International Conference on Computational Intelligence and Applications (ICCIA) Pub Date : 2021-06-01 DOI: 10.1109/ICCIA52886.2021.00013

Danqing Pu, Zhurong Zhou

引用次数: 0

CapBind: Prediction of Transcription Factor Binding Sites Based on Capsule Network CapBind:基于胶囊网络的转录因子结合位点预测

2021 6th International Conference on Computational Intelligence and Applications (ICCIA) Pub Date : 2021-06-01 DOI: 10.1109/ICCIA52886.2021.00014

Jiandong Cheng, Zihang Wang, Yirong Liu, Wei Huang

引用次数: 0

evolved Local Dynamic Map (eLDM) for Vehicles of Future 为未来车辆改进的局部动态地图(eLDM)

2021 6th International Conference on Computational Intelligence and Applications (ICCIA) Pub Date : 2021-06-01 DOI: 10.1109/ICCIA52886.2021.00063

Fatima Almheiri, Maryam Alyileili, Reem Alneyadi, Beshair Alahbabi, Manzoor Khan, Hesham El-Sayed

{"title":"evolved Local Dynamic Map (eLDM) for Vehicles of Future","authors":"Fatima Almheiri, Maryam Alyileili, Reem Alneyadi, Beshair Alahbabi, Manzoor Khan, Hesham El-Sayed","doi":"10.1109/ICCIA52886.2021.00063","DOIUrl":"https://doi.org/10.1109/ICCIA52886.2021.00063","url":null,"abstract":"With the advent of new technologies, the world will soon witness fully autonomous vehicles (AVs). AVs implement different layers including: perception, behavior and control. One major component that realizes the objectives of autonomous vehicles is Local Dynamic Map (LDM). Although the objectives of automation levels (0-3) were achieved though the existing standardized LDM, the higher levels of automation for AVs (i.e., Level 4 and Level 5) cannot be achieved owing to the complex dynamics of environment and fully independence from a human driver. The challenges of higher levels of automation include: accurate object detection and environment understanding of complex environments. Sharp turns, complex roundabouts, presences of Vulnerable Road Users, blind spots, and unprecedented events are some of the complex events, which are not captured by the LDM of today. Hence, in this paper, we propose a novel approach of introducing additional layers of information, which are populated through the information from external sources e.g., on-road deployed sensors, edges, etc. We term our contributed LDM as evolved LDM (eLDM). We extensively implement the proposed eLDM by working with IoT middleware, technologies like Thingsboard, Adobe XD and Google Web Designer. We created a new eLDM for vehicle and exploited the IoT middleware for aggregating the local (data collected from on-vehicle deployed sensors) and external (data collected from RSUs). To validate the contribution, we tested: the communication, the features of implemented IoT middleware, interface of the middleware with the implemented eLDM. The experiments validated the proper functioning of the developed components and inter-components interaction. The validation was carried out in the real settings i.e., in the UAEU campus with Golf carts.","PeriodicalId":269269,"journal":{"name":"2021 6th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"21 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":"128238023","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

Discovery of Object Concepts in Academic Field Based on Deep Learning 基于深度学习的学术领域对象概念发现

2021 6th International Conference on Computational Intelligence and Applications (ICCIA) Pub Date : 2021-06-01 DOI: 10.1109/ICCIA52886.2021.00009

Jie Yu, Junwei Wang, Chenle Pan, Yaliu Li

引用次数: 0

A Single Source Reachability Query Method for Gene Regulatory Networks 基因调控网络的单源可达性查询方法

2021 6th International Conference on Computational Intelligence and Applications (ICCIA) Pub Date : 2021-06-01 DOI: 10.1109/ICCIA52886.2021.00060

Zhaoyuan Zhang, Zhiqiong Wang, Ziheng Ding, Keyi Liu, Hanwen Wang, Weiyiqi Wang

{"title":"A Single Source Reachability Query Method for Gene Regulatory Networks","authors":"Zhaoyuan Zhang, Zhiqiong Wang, Ziheng Ding, Keyi Liu, Hanwen Wang, Weiyiqi Wang","doi":"10.1109/ICCIA52886.2021.00060","DOIUrl":"https://doi.org/10.1109/ICCIA52886.2021.00060","url":null,"abstract":"With the deepening of research on gene regulatory network, the construction technology of it has been relatively mature. However, according to the characteristics of gene regulatory network, it is still a problem to realize efficient reachable probability query among gene pairs on constructed gene regulatory network. Therefore, this paper proposed an efficient and accurate single-source reachability query algorithm GRN-RQ based on gene regulatory network. Single-source means: the reachability query between gene pairs with both single initial node and single destination node. Algorithm GRN-RQ mainly includes two parts, respectively, an active graph pruning algorithm AP, that is applicable to different node situations, is used to reduce the size of probability graphs, a concurrent reachability query algorithm PSRA for partial instance graph generation and staged graph search, which is used to improve operational efficiency. Through experimental verification, the algorithm GRN-RQ proposed in this paper can not only quickly obtain the reachable probability between gene pairs, but also improve the accuracy of result compared with the traditional method.","PeriodicalId":269269,"journal":{"name":"2021 6th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"81 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":"130209556","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

Attention based Subregion Aggregation Graph Convolution Networks with Extended Neighborhood 基于注意力的扩展邻域子区域聚集图卷积网络

2021 6th International Conference on Computational Intelligence and Applications (ICCIA) Pub Date : 2021-06-01 DOI: 10.1109/ICCIA52886.2021.00064

Shijie Tang, Hongtao Wei

{"title":"Attention based Subregion Aggregation Graph Convolution Networks with Extended Neighborhood","authors":"Shijie Tang, Hongtao Wei","doi":"10.1109/ICCIA52886.2021.00064","DOIUrl":"https://doi.org/10.1109/ICCIA52886.2021.00064","url":null,"abstract":"Graph Convolution Network (GCN) is a powerful model for graph representation learning. But affected by limited scope of neighborhood and average aggregation. GCNs unable to capture the feature representations from distant nodes, and lose the structural correlation and attribute correlation between nodes. Mapping nodes to a latent-space and building extended neighborhood can improve the problem, in theory. But the irrelevant messages of latent-space neighborhood can adversely affect the performance, and the experiments of predecessors showed that the disadvantages of latent-space neighborhood outweigh the advantages. In this paper, we propose an attention based subregion aggregation graph convolution networks, termed AG-GCN, an efficient representation learning model for node classification to overcome the weaknesses. AG-GCN utilize graph embedding to map the nodes that have the same label with the target node to its neighborhood in the vector space to build extended neighborhood, so the long-range dependencies can be captured. What’s more, we overcome the adverse effects of irrelevant messages from extended neighborhood, and catch the structural correlation as well as attribute correlation by multi region attention mechanism. Our experimental results show that combining network geometry and attention computation yields a general improvement of accuracy on most range of open datasets of graphs.","PeriodicalId":269269,"journal":{"name":"2021 6th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"8 24 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":"132358157","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 the Probability Design of Missile Mass Characteristic Deviation Basedon Monte Carlo Method 基于蒙特卡罗方法的导弹质量特性偏差概率设计研究

2021 6th International Conference on Computational Intelligence and Applications (ICCIA) Pub Date : 2021-06-01 DOI: 10.1109/ICCIA52886.2021.00021

Shicai Si, Zhang Xin, Wang Yue, Changmao Qin

引用次数: 0