2022 2nd International Symposium on Artificial Intelligence and its Application on Media (ISAIAM)最新文献_第2页

Surface Defect Data set Enhancement method for wind Turbine based on RES-DCGAN 基于RES-DCGAN的风力机表面缺陷数据集增强方法

2022 2nd International Symposium on Artificial Intelligence and its Application on Media (ISAIAM) Pub Date : 2022-06-01 DOI: 10.1109/ISAIAM55748.2022.00023

Shiyu Zhou, Hong‐lei Ma

引用次数: 0

Overview of the development of AI dataset annotation 人工智能数据集标注的发展概况

2022 2nd International Symposium on Artificial Intelligence and its Application on Media (ISAIAM) Pub Date : 2022-06-01 DOI: 10.1109/ISAIAM55748.2022.00041

Bochao Ao, Bingbing Fan

引用次数: 0

Study on the influence of safety signs on people's attention based on intelligent eye tracker 基于智能眼动仪的安全标志对人注意力影响的研究

2022 2nd International Symposium on Artificial Intelligence and its Application on Media (ISAIAM) Pub Date : 2022-06-01 DOI: 10.1109/ISAIAM55748.2022.00035

Juncai Yu, Daojun Han

{"title":"Study on the influence of safety signs on people's attention based on intelligent eye tracker","authors":"Juncai Yu, Daojun Han","doi":"10.1109/ISAIAM55748.2022.00035","DOIUrl":"https://doi.org/10.1109/ISAIAM55748.2022.00035","url":null,"abstract":"This article uses eye tracker to record the subjects' corresponding experimental data, and analyzes the influence of location settings on the significance of safety signs. This article discusses the effect of the location of the signs on the significance of the safety signs. This study used eye movement and reaction time methods to investigate the hazard perception ability of young drivers in special road environments. This research hypothesizes that having traffic safety signs will promote the driver's reaction time to hazards, but the safety signs will not speed up the driver's visual search time for hazards. With the help of eye tracker, 30 subjects were recorded when they identified the safety signs at 6 locations. Combined with Tobii's visual analysis and statistical analysis, the fixation duration was used as a quantitative indicator for the participants to evaluate the significance of safety signs. The results show that when the safety signs are set on the right or upper right, the red area in the heat map of the visualization analysis is larger and more concentrated, and the number of fixation points in the area of interest is larger. This position can better enhance the distinctiveness of the safety signs.","PeriodicalId":382895,"journal":{"name":"2022 2nd International Symposium on Artificial Intelligence and its Application on Media (ISAIAM)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121907754","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

Simulated Annulling in Convolutional Neural Network 卷积神经网络中的模拟环化

2022 2nd International Symposium on Artificial Intelligence and its Application on Media (ISAIAM) Pub Date : 2022-06-01 DOI: 10.1109/ISAIAM55748.2022.00015

Chenqi Zhou

{"title":"Simulated Annulling in Convolutional Neural Network","authors":"Chenqi Zhou","doi":"10.1109/ISAIAM55748.2022.00015","DOIUrl":"https://doi.org/10.1109/ISAIAM55748.2022.00015","url":null,"abstract":"Deep learning is a new branch of machine learning research with the goal of bringing us closer to artificial intelligence. This approach can learn several layers to abstract and represent in order to generate a shared understanding of dataset like text, music, and image. Even though DL is effective in wide range, it is difficult to train. Stochastic Gradient Descent and Conjugate Gradient have been offered as approaches for training DL to make it effective. This paper aims to propose Simulated Annealing (SA) as an alternative way for optimum DL employing a current optimization technique, namely a metaheuristic algorithm, to enhance the effectiveness of Convolution Neural Network (CNN). Two classical CNN models AlexNet and ResNet are used for the experiment. The suggested method is tested by the CIFAR-10 dataset to confirm its correctness and efficiency. In addition, we compare our proposed solution to CNN's original at different standards, such as model accuracy, test error rate and learning efficiency. After the experiment, it can be concluded that despite the longer computation time, the results of the experiments suggest that the proposed approach of this paper can enhance the effectiveness of several models of CNN, such as AlexNet and ResNet34.","PeriodicalId":382895,"journal":{"name":"2022 2nd International Symposium on Artificial Intelligence and its Application on Media (ISAIAM)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115033690","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 CycleGAN for natural scenery images style transfer 改进CycleGAN自然风光图像风格转移

2022 2nd International Symposium on Artificial Intelligence and its Application on Media (ISAIAM) Pub Date : 2022-06-01 DOI: 10.1109/ISAIAM55748.2022.00011

Yueshan Cui, Yizhong Luan, Junmei Guo

{"title":"Improved CycleGAN for natural scenery images style transfer","authors":"Yueshan Cui, Yizhong Luan, Junmei Guo","doi":"10.1109/ISAIAM55748.2022.00011","DOIUrl":"https://doi.org/10.1109/ISAIAM55748.2022.00011","url":null,"abstract":"Natural scenery images style transfer is a technique using computer technology to change the stylization effects of images by processing the high-level features which are extracted by images in neural networks, and is used to improve the diversities and aesthetics of images. Since existing neural network models cannot achieve a good effect when dealing with the style transfer tasks of natural photos, this paper proposes an improved CycleGAN method that has the advantage of changing two unpaired image datasets in style. In order to save more image content and solve the model overfitting problem, we added a channel attention mechanism to the generator and optimized the cycle consistency loss. We defined the developed loss function as MS-SSIM+SmoothL1 in this paper. The method can alleviate the overfitting phenomenon of the model as the epoch increases. The images generated by our proposed method have better performance in detail. Experiments demonstrate that the images generated by our proposed improved network are more correspond with human perception in visual. In the FID score, our proposed method was 42.24% lower in the Summer2winter datasets and 23.76% lower in the Monet2photo datasets than CycleGAN.","PeriodicalId":382895,"journal":{"name":"2022 2nd International Symposium on Artificial Intelligence and its Application on Media (ISAIAM)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130154642","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

Interaction design of hall intelligent controller based on user behavior characteristics 基于用户行为特征的大厅智能控制器交互设计

2022 2nd International Symposium on Artificial Intelligence and its Application on Media (ISAIAM) Pub Date : 2022-06-01 DOI: 10.1109/ISAIAM55748.2022.00040

Yi Wang, Xuanming Feng, Lixian Jiang, Heng Zhang, Yiran Pang

{"title":"Interaction design of hall intelligent controller based on user behavior characteristics","authors":"Yi Wang, Xuanming Feng, Lixian Jiang, Heng Zhang, Yiran Pang","doi":"10.1109/ISAIAM55748.2022.00040","DOIUrl":"https://doi.org/10.1109/ISAIAM55748.2022.00040","url":null,"abstract":"With the development of the with the development of the Internet of things and smart home, consumers have put forward higher demands for the integration, emotion and individuation of smart home device controllers. Through the behavior of users in and out of the gate video tracking, determine the user requirements and the basic function of the vestibular intelligent controller interface. Based on user behavior demand in and out of the gate, starting from the multi-sensory interactive design, visual design principles of combining multi-sensory human-computer interaction interface, through the “Increase visual and auditory immersion through animations that simulate real situations” and “Icon metaphorical expression and quasi-physical design improve ease of use” and “The combination of dynamic and static interaction increases sensory experience” three ways of improving vestibular intelligent controller using experience. This paper provides a feasible research direction for the improvement of hall intelligent controller interaction design.","PeriodicalId":382895,"journal":{"name":"2022 2nd International Symposium on Artificial Intelligence and its Application on Media (ISAIAM)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134553964","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

Analysis of Urban Landscape Change Based on Remote Sensing 基于遥感的城市景观变化分析

2022 2nd International Symposium on Artificial Intelligence and its Application on Media (ISAIAM) Pub Date : 2022-06-01 DOI: 10.1109/ISAIAM55748.2022.00037

Songyan Wang, Xiaolu Huang, Zhe Wang, Qi Xue

{"title":"Analysis of Urban Landscape Change Based on Remote Sensing","authors":"Songyan Wang, Xiaolu Huang, Zhe Wang, Qi Xue","doi":"10.1109/ISAIAM55748.2022.00037","DOIUrl":"https://doi.org/10.1109/ISAIAM55748.2022.00037","url":null,"abstract":"In this paper, using the multispectral and panchromatic images of the main urban area as experimental data, a method for analyzing dynamic changes of urban landscape based on remote sensing is proposed. The results of landscape elements are obtained through the LVQ2 neural network classification method. From the perspective of patch characteristics, the characteristics of the target urban landscape pattern were analyzed, and the urban change trend was summarized by combining the two-phase images and the transition matrix. The results show that: (1) the number of vegetation in this area has decreased, the area of building land, general land, rivers, and cultivated land has increased, and the greening situation of the city is declining, and the land use has turned to the functional land that improves people's production efficiency; The fragmentation of the landscape patches has decreased, and the connectivity of the landscape has increased. The city government or relevant departments have made overall planning for its overall layout, focusing on the overall distribution of functional areas and various landscapes. The research results of this paper are of great significance for macroscopically grasping the current situation of urban landscape and serving the government and related enterprises and institutions.","PeriodicalId":382895,"journal":{"name":"2022 2nd International Symposium on Artificial Intelligence and its Application on Media (ISAIAM)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132862806","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 Crowdsourcing-oriented Global Complex Task Assignment Based on Artificial Intelligence 面向众包的人工智能全局复杂任务分配研究

2022 2nd International Symposium on Artificial Intelligence and its Application on Media (ISAIAM) Pub Date : 2022-06-01 DOI: 10.1109/ISAIAM55748.2022.00021

Jinwei Zhang, Jinpeng Wei

{"title":"Research on Crowdsourcing-oriented Global Complex Task Assignment Based on Artificial Intelligence","authors":"Jinwei Zhang, Jinpeng Wei","doi":"10.1109/ISAIAM55748.2022.00021","DOIUrl":"https://doi.org/10.1109/ISAIAM55748.2022.00021","url":null,"abstract":"In the traditional crowdsourcing platform, every time a complex task is published, a new team needs to be formed from the system to meet the skill requirements of the task. However, this one-sided consideration of the assignment of tasks not only fails to enable workers to perform the appropriate tasks to the best of their ability, but also the number of successful tasks. This becomes even more difficult when a large number of complex tasks are distributed across the globe. The goal of this study is to focus on tasks and the assignment of global workers: to maximize the number of tasks successfully assigned, and to maximize the effort of the workers to complete the appropriate tasks. Then the task assignment process is abstracted into a weighted bipartite graph matching model, which is solved by an improved KM algorithm. Finally, experiments are carried out on real data sets, and the results show that, compared with the previous methods, the method proposed in this paper has achieved good results in increasing the number of successful assignments, improving work efficiency and reducing cost.","PeriodicalId":382895,"journal":{"name":"2022 2nd International Symposium on Artificial Intelligence and its Application on Media (ISAIAM)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125025440","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

Motion Deblur with Non-Local Attention Network 非局部注意网络的运动去模糊

2022 2nd International Symposium on Artificial Intelligence and its Application on Media (ISAIAM) Pub Date : 2022-06-01 DOI: 10.1109/ISAIAM55748.2022.00029

Shihuai Zhang, Xiaoyu Li

引用次数: 0

Influencing Factors Analysis of Development of Film Base With Multiple Logistic Regression Model 基于多元Logistic回归模型的薄膜基地发展影响因素分析

2022 2nd International Symposium on Artificial Intelligence and its Application on Media (ISAIAM) Pub Date : 2022-06-01 DOI: 10.1109/ISAIAM55748.2022.00022

Yanting Gao, Zixing Zhang

{"title":"Influencing Factors Analysis of Development of Film Base With Multiple Logistic Regression Model","authors":"Yanting Gao, Zixing Zhang","doi":"10.1109/ISAIAM55748.2022.00022","DOIUrl":"https://doi.org/10.1109/ISAIAM55748.2022.00022","url":null,"abstract":"Since its inception in the last century, Chinese film and TV bases have faced the problems of rapid growth in quantity and unbalanced development in quality. The existing research generally expects that the financial investment of local governments and the agglomeration of local cultural industries can improve the level of industrial development of film bases and believe that the development of film base industries is affected by regions. However, the existing theoretical research has failed to give strong support to these optimistic expectations. Based on relevant finance and economics databases, this study conducts correlation analysis and multiple logistic regression to test these optimistic proposals. The results show that there is a significant correlation between the development level of film bases and the government financial support, the cultural industry agglomeration, and transportation accessibility. However, the effect of the area where the base is located is not significant. In addition, the research builds a computational model based on multiple logistic regression to predict the development level of film bases and tries to provide a reference for the development of the film industry.","PeriodicalId":382895,"journal":{"name":"2022 2nd International Symposium on Artificial Intelligence and its Application on Media (ISAIAM)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132663789","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