首页 > 最新文献

2020 2nd International Conference on Information Technology and Computer Application (ITCA)最新文献

英文 中文
An Evaluation Algorithm for Expert in Community Question Answering by Combining Topics and Behaviors 主题与行为相结合的社区问答专家评价算法
Minxing Wang, Bin Wu
In this paper, we propose an algorithm to evaluate the influence of experts in community question answering (CQA). In the current research of influence evaluation algorithm, the main research method is to establish the network between users and problems, and use centrality algorithm such as PageRank to evaluate the influence of users. However, Existing algorithms tend to favor users with more followers. In this paper, we propose an evaluation algorithm based on user’s content combined with link relationship. The experimental results show that our method can give higher ratings to users who have low number of followers but can provide high-quality content. At the same time, we add the topic relevance to the evaluation algorithm, so that the expert score will change according to the different topics.
在本文中,我们提出了一种评估专家在社区问答(CQA)中的影响力的算法。在目前对影响力评价算法的研究中,主要的研究方法是建立用户与问题之间的网络,利用PageRank等中心性算法对用户的影响力进行评价。然而,现有的算法倾向于支持拥有更多关注者的用户。本文提出了一种基于用户内容结合链接关系的评价算法。实验结果表明,我们的方法可以对关注者数量较少但能够提供高质量内容的用户给予较高的评分。同时,我们在评价算法中加入了主题相关性,使得专家评分会根据不同的主题而变化。
{"title":"An Evaluation Algorithm for Expert in Community Question Answering by Combining Topics and Behaviors","authors":"Minxing Wang, Bin Wu","doi":"10.1109/ITCA52113.2020.00021","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00021","url":null,"abstract":"In this paper, we propose an algorithm to evaluate the influence of experts in community question answering (CQA). In the current research of influence evaluation algorithm, the main research method is to establish the network between users and problems, and use centrality algorithm such as PageRank to evaluate the influence of users. However, Existing algorithms tend to favor users with more followers. In this paper, we propose an evaluation algorithm based on user’s content combined with link relationship. The experimental results show that our method can give higher ratings to users who have low number of followers but can provide high-quality content. At the same time, we add the topic relevance to the evaluation algorithm, so that the expert score will change according to the different topics.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"157 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134515033","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
SWOT Analysis of Satellite Mobile Communication System Based on GAHP 基于GAHP的卫星移动通信系统SWOT分析
Nana Zhang, Xiaotao Xu, Xiafeng Jiang, Jiangcheng Pang
Based on the current communication situation and the requirements of future development for satellite communication, first introduce the GAHP-SWOT evaluation method, SWOT analysis is also carried out on the key elements affecting the development tactics of satellite mobile communication system, so as to construct the evaluation index system framework of its development tactics. Then, according to the relevant steps of GAHP-SWOT analysis method, the SWOT elements and indexes of the development tactics are gradually analyzed, and a series of model algorithms are used to evaluate the advantages and disadvantages of the development tactics, and finally a reasonable development tactic is established, and the optimization suggestions for the future development tactics of satellite mobile communication system are given.
根据卫星通信的现状和未来发展的要求,首先介绍GAHP-SWOT评价方法,并对影响卫星移动通信系统发展战术的关键要素进行SWOT分析,从而构建其发展战术评价指标体系框架。然后,按照GAHP-SWOT分析法的相关步骤,逐步分析发展战术的SWOT要素和指标,并运用一系列模型算法对发展战术的优劣进行评价,最终建立合理的发展战术,并对卫星移动通信系统未来发展战术提出优化建议。
{"title":"SWOT Analysis of Satellite Mobile Communication System Based on GAHP","authors":"Nana Zhang, Xiaotao Xu, Xiafeng Jiang, Jiangcheng Pang","doi":"10.1109/ITCA52113.2020.00085","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00085","url":null,"abstract":"Based on the current communication situation and the requirements of future development for satellite communication, first introduce the GAHP-SWOT evaluation method, SWOT analysis is also carried out on the key elements affecting the development tactics of satellite mobile communication system, so as to construct the evaluation index system framework of its development tactics. Then, according to the relevant steps of GAHP-SWOT analysis method, the SWOT elements and indexes of the development tactics are gradually analyzed, and a series of model algorithms are used to evaluate the advantages and disadvantages of the development tactics, and finally a reasonable development tactic is established, and the optimization suggestions for the future development tactics of satellite mobile communication system are given.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132586246","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 New Method for information security risk management in big data environment 大数据环境下信息安全风险管理新方法
Zhengqi Zhang
In recent years, the social security problems are becoming more and more complex, and the public security work is arduous. The traditional governance mode needs more transformation and bigger upgrading. At present, the police information processing work lacks of effective information data support. By using advanced technologies such as big data and artificial intelligence, the police information big data application platform is constructed to more effectively gather information related to the police situation, dig deeply into the police information data resources, and expand the application according to police information business. In order to achieve a more comprehensive source of police information, more efficient business processing, and more positive service to the grassroots, we need accurate prediction and decision support. So as to promote the transformation of public security policing mode from extensive manpower type to intelligent fine type, this paper propose a new method based private matching protocol for information security risk management in big data environment, and provide security analysis at the last.
近年来,社会治安问题日益复杂,公安工作十分繁重。传统的治理模式需要更多的转型和更大的升级。目前,公安机关的信息处理工作缺乏有效的信息数据支持。利用大数据、人工智能等先进技术,构建警务信息大数据应用平台,更有效地采集与警务形势相关的信息,深入挖掘警务信息数据资源,并根据警务信息业务拓展应用。为了实现更全面的警务信息来源,更高效的业务处理,更积极的服务于基层,我们需要准确的预测和决策支持。为推动公安警务模式由粗放型人力型向智能化精细化型转变,本文提出了一种基于私有匹配协议的大数据环境下信息安全风险管理新方法,并在最后进行了安全分析。
{"title":"A New Method for information security risk management in big data environment","authors":"Zhengqi Zhang","doi":"10.1109/ITCA52113.2020.00100","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00100","url":null,"abstract":"In recent years, the social security problems are becoming more and more complex, and the public security work is arduous. The traditional governance mode needs more transformation and bigger upgrading. At present, the police information processing work lacks of effective information data support. By using advanced technologies such as big data and artificial intelligence, the police information big data application platform is constructed to more effectively gather information related to the police situation, dig deeply into the police information data resources, and expand the application according to police information business. In order to achieve a more comprehensive source of police information, more efficient business processing, and more positive service to the grassroots, we need accurate prediction and decision support. So as to promote the transformation of public security policing mode from extensive manpower type to intelligent fine type, this paper propose a new method based private matching protocol for information security risk management in big data environment, and provide security analysis at the last.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133241956","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
A Robust Routing Algorithm with Dynamic Minimum Hop Selection in Wireless Sensor Networks with Unreliable Links 链路不可靠无线传感器网络中动态最小跳数选择的鲁棒路由算法
Yuanjia Ma, Marifel Capili Kummer
The efficient routing poses to be one of the main issues encountered in wireless sensor networks, and, in recent years, there has been carried out extensive investigation of the optimization method of energy and latency. Nonetheless, little work has already been done under austere conditions, for instance, chemical plants, oil fields, nuclear power plant, and the battlefield with unreliable links. So, it appears to be a new challenging point of concern that how to ensure the stability as well as reliability of data transmission under the high risk environment. In this research work, we have introduced a robust routing protocol, a novel design algorithm with dynamic minimum hop selection (DMHS) by dynamic programming. The major idea is making the probabilistic forwarding decisions for the utilization of a distributed routing discovery strategy with the node’s minimum hop dynamic adjustment. Simulation experiments revealed that, in comparison with conventional energy efficiency algorithm, the DMHS algorithm offers approximately 15% increases of lifetime more than 700 nodes, in addition to having better performance on average delivery rate at the nodes death rate from 20% to 60%.
有效路由是无线传感器网络中遇到的主要问题之一,近年来,人们对能量和时延的优化方法进行了广泛的研究。然而,在化学工厂、油田、核电站、连接不可靠的战场等恶劣条件下,几乎没有进行过任何工作。因此,如何在高风险环境下保证数据传输的稳定性和可靠性成为一个新的挑战。本文提出了一种基于动态规划的动态最小跳数选择(DMHS)鲁棒路由协议。其主要思想是利用节点最小跳数动态调整的分布式路由发现策略进行概率转发决策。仿真实验表明,与传统的能效算法相比,DMHS算法在超过700个节点时,寿命提高了约15%,并且在节点死亡率从20%到60%的情况下,平均投递率也有更好的表现。
{"title":"A Robust Routing Algorithm with Dynamic Minimum Hop Selection in Wireless Sensor Networks with Unreliable Links","authors":"Yuanjia Ma, Marifel Capili Kummer","doi":"10.1109/ITCA52113.2020.00015","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00015","url":null,"abstract":"The efficient routing poses to be one of the main issues encountered in wireless sensor networks, and, in recent years, there has been carried out extensive investigation of the optimization method of energy and latency. Nonetheless, little work has already been done under austere conditions, for instance, chemical plants, oil fields, nuclear power plant, and the battlefield with unreliable links. So, it appears to be a new challenging point of concern that how to ensure the stability as well as reliability of data transmission under the high risk environment. In this research work, we have introduced a robust routing protocol, a novel design algorithm with dynamic minimum hop selection (DMHS) by dynamic programming. The major idea is making the probabilistic forwarding decisions for the utilization of a distributed routing discovery strategy with the node’s minimum hop dynamic adjustment. Simulation experiments revealed that, in comparison with conventional energy efficiency algorithm, the DMHS algorithm offers approximately 15% increases of lifetime more than 700 nodes, in addition to having better performance on average delivery rate at the nodes death rate from 20% to 60%.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"179 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114208863","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
Application of microexpressions analysis based on deep learning in the service industry 基于深度学习的微表情分析在服务业中的应用
Lu Shang, Lunan Liu, Liying Sui, Dexue Zhang
Micro-expression is a spontaneous expression that cannot be suppressed by humans and an important way to reveal hidden emotions. In order to respond to the increasing service demand and improve service quality, the application of deep learning micro-expression analysis in the service industry can not only detect the service quality of service personnel, evaluate and score service personnel in real time, but also perform real-time evaluation and evaluation of service personnel. Score, it can also detect the emotional changes of the served person in real time and formulate corresponding service strategies. This article uses a 13- layer VGG structure convolution model. The experimental results show that the model can accurately analyze the changes in the expressions of the characters, indicating that the micro-expression analysis of deep learning is feasible in the service industry.
微表情是人类无法抑制的自发表达,是揭示隐藏情绪的重要方式。为了应对日益增长的服务需求,提高服务质量,深度学习微表情分析在服务业中的应用,不仅可以实时检测服务人员的服务质量,对服务人员进行评价和评分,还可以对服务人员进行实时评价和评价。评分后,还可以实时检测被服务者的情绪变化,并制定相应的服务策略。本文采用了一个13层的VGG结构卷积模型。实验结果表明,该模型能够准确分析人物表情的变化,表明深度学习的微表情分析在服务业中是可行的。
{"title":"Application of microexpressions analysis based on deep learning in the service industry","authors":"Lu Shang, Lunan Liu, Liying Sui, Dexue Zhang","doi":"10.1109/itca52113.2020.00030","DOIUrl":"https://doi.org/10.1109/itca52113.2020.00030","url":null,"abstract":"Micro-expression is a spontaneous expression that cannot be suppressed by humans and an important way to reveal hidden emotions. In order to respond to the increasing service demand and improve service quality, the application of deep learning micro-expression analysis in the service industry can not only detect the service quality of service personnel, evaluate and score service personnel in real time, but also perform real-time evaluation and evaluation of service personnel. Score, it can also detect the emotional changes of the served person in real time and formulate corresponding service strategies. This article uses a 13- layer VGG structure convolution model. The experimental results show that the model can accurately analyze the changes in the expressions of the characters, indicating that the micro-expression analysis of deep learning is feasible in the service industry.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116447396","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 Vehicle Detection Based on YOLOv3 基于YOLOv3的车辆检测研究
X. Chaojun, Ye Qing, Liu Jianxiong, L. Liang
In order to improve the recognition accuracy and detection speed of vehicle models, a vehicle model detection based on the improved YOLOv3 model is proposed. On the one hand, the SENet structure is introduced into the feature extraction network, and the weight optimization rules of features in the convolution process are added; On the other hand, the number of high-level repeated convolutional layers of the feature extraction network is improved to improve the time cost of the model in vehicle type detection. The test results on the BIT-Vehicle dataset show that the proposed method improves the recognition speed relative to YOLO v3 by about 24% on the premise of ensuring the vehicle model recognition accuracy, and verifies the effectiveness of the proposed target detection method.
为了提高车辆模型的识别精度和检测速度,提出了一种基于改进YOLOv3模型的车辆模型检测方法。一方面,在特征提取网络中引入SENet结构,并在卷积过程中加入特征的权值优化规则;另一方面,改进了特征提取网络的高级重复卷积层数,提高了模型在车型检测中的时间成本。在BIT-Vehicle数据集上的测试结果表明,在保证车辆模型识别精度的前提下,所提方法相对于YOLO v3的识别速度提高了24%左右,验证了所提目标检测方法的有效性。
{"title":"Research on Vehicle Detection Based on YOLOv3","authors":"X. Chaojun, Ye Qing, Liu Jianxiong, L. Liang","doi":"10.1109/ITCA52113.2020.00097","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00097","url":null,"abstract":"In order to improve the recognition accuracy and detection speed of vehicle models, a vehicle model detection based on the improved YOLOv3 model is proposed. On the one hand, the SENet structure is introduced into the feature extraction network, and the weight optimization rules of features in the convolution process are added; On the other hand, the number of high-level repeated convolutional layers of the feature extraction network is improved to improve the time cost of the model in vehicle type detection. The test results on the BIT-Vehicle dataset show that the proposed method improves the recognition speed relative to YOLO v3 by about 24% on the premise of ensuring the vehicle model recognition accuracy, and verifies the effectiveness of the proposed target detection method.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114617771","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
Research on Private Cloud Storage Method of Marketing Information Based on Grid Technology 基于网格技术的营销信息私有云存储方法研究
Yang Guo, Jia Xu
Enterprise marketing information is stored in the form of message files or databases, which is increasing exponentially. Under the conditions of information failure, the backup is not timely, resulting in a decrease in storage efficiency. Therefore, research on the private cloud storage method of marketing information is performed based on grid technology. Moreover, grid basic services are provided through grid system management nodes and grid public service nodes, and local resource servers and enterprise grid application services are used to provide grid application services. Based on each server node in the model, the virtual machine usage is adjusted through the load forecasting process, and the mirroring backup process is applied to restore the virtual machine data under fault conditions. In addition, the model uses the longest path matching method to manage marketing information metadata based on metadata logical search and location metadata sub-table. Experimental results show that the load of different virtual machines in the marketing information storage process is less than 40%, and the load of each virtual machine is basically the same, indicating that the method proposed in the paper can enhance the balance of blocking in the information storage process and improve storage efficiency.
企业营销信息以消息文件或数据库的形式存储,呈指数级增长。在信息失效的情况下,备份不及时,导致存储效率降低。因此,本文基于网格技术对营销信息私有云存储方法进行了研究。通过网格系统管理节点和网格公共服务节点提供网格基础服务,利用本地资源服务器和企业网格应用服务提供网格应用服务。基于模型中的每个服务器节点,通过负载预测过程调整虚拟机的使用情况,并通过镜像备份过程恢复故障情况下的虚拟机数据。此外,该模型基于元数据逻辑搜索和位置元数据子表,采用最长路径匹配方法对营销信息元数据进行管理。实验结果表明,营销信息存储过程中不同虚拟机的负载小于40%,且每个虚拟机的负载基本相同,表明本文提出的方法可以增强信息存储过程中阻塞的平衡性,提高存储效率。
{"title":"Research on Private Cloud Storage Method of Marketing Information Based on Grid Technology","authors":"Yang Guo, Jia Xu","doi":"10.1109/ITCA52113.2020.00111","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00111","url":null,"abstract":"Enterprise marketing information is stored in the form of message files or databases, which is increasing exponentially. Under the conditions of information failure, the backup is not timely, resulting in a decrease in storage efficiency. Therefore, research on the private cloud storage method of marketing information is performed based on grid technology. Moreover, grid basic services are provided through grid system management nodes and grid public service nodes, and local resource servers and enterprise grid application services are used to provide grid application services. Based on each server node in the model, the virtual machine usage is adjusted through the load forecasting process, and the mirroring backup process is applied to restore the virtual machine data under fault conditions. In addition, the model uses the longest path matching method to manage marketing information metadata based on metadata logical search and location metadata sub-table. Experimental results show that the load of different virtual machines in the marketing information storage process is less than 40%, and the load of each virtual machine is basically the same, indicating that the method proposed in the paper can enhance the balance of blocking in the information storage process and improve storage efficiency.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114626734","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
Melanoma Classification Using Deep Convolutional Neural Networks with Ensemble Scheme 基于集成方案的深度卷积神经网络黑素瘤分类
Dewei Chen, Zhang Ziyuan, H. Ji, Yuxin Huang
Among many skin diseases, melanoma is the most common and deadly malignant skin cancer which seriously threatens people’s physical health. An effective way to treat melanoma is to use dermoscopic images for early diagnosis. With the limited highly-trained experts, deep learning can be an alternative for melanoma classification. In this paper, we adopt the convolutional neural networks (CNNs) model, i.e., EfficientNet [1], along with ensemble schemes to solve the melanoma classification problem. The EfficientNet model can design the proper network architecture to extract features with better accuracy and efficiency than other CNNs. In order to solve the problem of data imbalance and try multiple parameter designs, we construct six different basic EfficientNet model and integrate their predictions. We conduct experiments on dataset released by a Kaggle competition. The experiments results show that our approach achieves 0.950 AUC score on the validation set, outperforming VGG16 and VGG19 [2] by 0.059 and 0.028 respectively, which verify the superiority of our CNN model and the improvement induced by the model ensemble strategy.
在众多皮肤病中,黑色素瘤是最常见、最致命的恶性皮肤癌,严重威胁着人们的身体健康。使用皮肤镜图像进行早期诊断是治疗黑色素瘤的有效方法。在训练有素的专家有限的情况下,深度学习可以成为黑色素瘤分类的另一种选择。在本文中,我们采用卷积神经网络(cnn)模型,即effentnet[1],结合集成方案来解决黑色素瘤分类问题。该模型可以通过设计合适的网络结构来提取特征,具有比其他cnn更好的准确性和效率。为了解决数据不平衡问题和尝试多参数设计,我们构建了6种不同的基本效率网络模型,并整合了它们的预测结果。我们在Kaggle竞赛发布的数据集上进行实验。实验结果表明,我们的方法在验证集上达到了0.950 AUC得分,分别比VGG16和VGG19[2]高出0.059和0.028,验证了我们的CNN模型的优越性以及模型集成策略带来的改进。
{"title":"Melanoma Classification Using Deep Convolutional Neural Networks with Ensemble Scheme","authors":"Dewei Chen, Zhang Ziyuan, H. Ji, Yuxin Huang","doi":"10.1109/ITCA52113.2020.00082","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00082","url":null,"abstract":"Among many skin diseases, melanoma is the most common and deadly malignant skin cancer which seriously threatens people’s physical health. An effective way to treat melanoma is to use dermoscopic images for early diagnosis. With the limited highly-trained experts, deep learning can be an alternative for melanoma classification. In this paper, we adopt the convolutional neural networks (CNNs) model, i.e., EfficientNet [1], along with ensemble schemes to solve the melanoma classification problem. The EfficientNet model can design the proper network architecture to extract features with better accuracy and efficiency than other CNNs. In order to solve the problem of data imbalance and try multiple parameter designs, we construct six different basic EfficientNet model and integrate their predictions. We conduct experiments on dataset released by a Kaggle competition. The experiments results show that our approach achieves 0.950 AUC score on the validation set, outperforming VGG16 and VGG19 [2] by 0.059 and 0.028 respectively, which verify the superiority of our CNN model and the improvement induced by the model ensemble strategy.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"15 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131844536","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 Survey on VQA: Datasets and Approaches VQA调查:数据集和方法
Yeyun Zou, Qiyu Xie
Visual question answering (VQA) is a task that combines both the techniques of computer vision and natural language processing. It requires models to answer a text-based question according to the information contained in a visual. In recent years, the research field of VQA has been expanded. Research that focuses on the VQA, examining the reasoning ability and VQA on scientific diagrams, has also been explored more. Meanwhile, more multimodal feature fusion mechanisms have been proposed. This paper will review and analyze existing datasets, metrics, and models proposed for the VQA task.
视觉问答(VQA)是计算机视觉和自然语言处理技术相结合的一项任务。它要求模型根据图像中包含的信息回答基于文本的问题。近年来,VQA的研究领域不断扩大。研究的重点是VQA,考察科学图表的推理能力和VQA,也得到了更多的探索。同时,还提出了更多的多模态特征融合机制。本文将回顾和分析为VQA任务提出的现有数据集、度量和模型。
{"title":"A Survey on VQA: Datasets and Approaches","authors":"Yeyun Zou, Qiyu Xie","doi":"10.1109/ITCA52113.2020.00069","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00069","url":null,"abstract":"Visual question answering (VQA) is a task that combines both the techniques of computer vision and natural language processing. It requires models to answer a text-based question according to the information contained in a visual. In recent years, the research field of VQA has been expanded. Research that focuses on the VQA, examining the reasoning ability and VQA on scientific diagrams, has also been explored more. Meanwhile, more multimodal feature fusion mechanisms have been proposed. This paper will review and analyze existing datasets, metrics, and models proposed for the VQA task.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"213 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132283564","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: 7
A Rapid Ear Modeling Method Based on Standard Template and Screening Algorithm for Portrait Product 基于标准模板和筛选算法的人像产品耳朵快速建模方法
Mingliang Wang, Cang Wu, Jialiang Li, Fuwei Duan
In view of the low efficiency in the conventional portrait modeling, a rapid ear modeling method based on a standard template and screening algorithm for portrait product is proposed to achieve high efficiency in portrait modeling. Firstly, the normalized template of ears can be obtained by the operation of normalizing the photo of ear and standard template. Secondly, the feature edge of the ear and standard template can be extracted respectively by using a method of edge detection based on gray-scale morphology and local threshold segmenting. Afterwards registration is performed. Thirdly, the extracted feature edges are analyzed through the proposed screening algorithm, and the optimal ear model is obtained from the library of the standard template. Therefore, a final portrait model achieved by assembly the optimal ear model to the original model. Finally, a case study of applying the proposed methodology to a personalized portrait product modeling demonstrates the feasibility and effectiveness of the proposed method.
针对传统人像建模效率低的问题,提出了一种基于标准模板和人像产品筛选算法的快速耳廓建模方法,实现了人像建模的高效率。首先,将耳朵照片与标准模板进行归一化处理,得到归一化的耳朵模板;其次,采用基于灰度形态学和局部阈值分割的边缘检测方法,分别提取耳朵的特征边缘和标准模板;之后进行注册。再次,通过所提筛选算法对提取的特征边缘进行分析,从标准模板库中得到最优耳模型;因此,通过将最优耳模型装配到原始模型中获得最终的人像模型。最后,将所提出的方法应用于个性化肖像产品建模的案例研究,验证了所提出方法的可行性和有效性。
{"title":"A Rapid Ear Modeling Method Based on Standard Template and Screening Algorithm for Portrait Product","authors":"Mingliang Wang, Cang Wu, Jialiang Li, Fuwei Duan","doi":"10.1109/ITCA52113.2020.00147","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00147","url":null,"abstract":"In view of the low efficiency in the conventional portrait modeling, a rapid ear modeling method based on a standard template and screening algorithm for portrait product is proposed to achieve high efficiency in portrait modeling. Firstly, the normalized template of ears can be obtained by the operation of normalizing the photo of ear and standard template. Secondly, the feature edge of the ear and standard template can be extracted respectively by using a method of edge detection based on gray-scale morphology and local threshold segmenting. Afterwards registration is performed. Thirdly, the extracted feature edges are analyzed through the proposed screening algorithm, and the optimal ear model is obtained from the library of the standard template. Therefore, a final portrait model achieved by assembly the optimal ear model to the original model. Finally, a case study of applying the proposed methodology to a personalized portrait product modeling demonstrates the feasibility and effectiveness of the proposed method.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133265122","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
期刊
2020 2nd International Conference on Information Technology and Computer Application (ITCA)
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1